ICPR 2008 - PDF Preprint Papers

ICPR 2008 International Conference on Pattern Recognition

3D Immersive Browsing | Click Here

Teaser Browsing | Click Here

Queue Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ICPR-2008 Paper

click to vote

ICPR
2008
IEEE

650views Computer Vision» more ICPR 2008»

Image mosaicing using local optical flow registration

2 years 3 months ago

Download www.moivre.usherbrooke.ca

Cylindrical panoramic mosaics can be created by aligning and stitching images from a series, captured by a camera rotating around its optical center. The transformation between tw...

François Deschênes, Marie Flavie Aucl...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status
1	650	Image mosaicing using local optical flow registration	claim
2	290	Seamless image-based texture atlases using multi-band blending	claim
3	283	Online Feature Evaluation For Object Tracking Using Kalman Filter
4	239	Object recognition and segmentation using SIFT and Graph Cuts	claim
5	220	Histogram of radon transform. A useful descriptor for shape retrieval	claim
6	158	Gait recognition by dynamic cues	claim
7	151	Adaptive local contrast enhancement for the visualization of high dynamic range images	claim
8	144	Robust log-Gabor filter for ear biometrics	claim
9	142	Saliency Cuts: An automatic approach to object segmentation	claim
10	138	V-LGBP: Volume based local Gabor binary patterns for face representation and recognition	claim
11	134	Retinal vessel tree segmentation using a deformable contour model	claim
12	132	Detection of anatomical landmarks in human colon from computed tomographic colonography images	claim
13	131	Evaluation of clustering methods for finding dominant optical flow fields in crowded scenes	claim
14	129	Invariant visual patterns for video copy detection	claim
15	125	Active contour algorithm for texture segmentation using a texture feature set	claim
16	123	3D reconstruction by combining shape from silhouette with stereo	claim
17	122	GPU-boosted online image matching	claim
18	122	A similarity measure under Log-Euclidean metric for stereo matching	claim
19	119	Discrete Pulse Transform of images: Algorithm and applications	claim
20	118	Real-time crowd motion analysis	claim
21	115	A new global shape prior for level set based segmentation	claim
22	115	Markerless human motion capture: An application of simulated annealing and Fast Marching Method	claim
23	115	Dunn's cluster validity index as a contrast measure of VAT images	claim
24	114	CDIKP: A highly-compact local feature descriptor	claim
25	113	Human appearance matching across multiple non-overlapping cameras	claim
26	110	Kernel bandwidth estimation in methods based on probability density function modelling	claim
27	107	Review and evaluation of commonly-implemented background subtraction algorithms	claim
28	103	Epipolar geometry and log-polar transform in wide baseline stereo matching	claim
29	101	Circular Earth Mover's Distance for the comparison of local features	claim
30	101	Robust and precise eye detection based on locally selective projection	claim
31	100	3D human posture estimation using the HOG features from monocular image	claim
32	99	3D gaze estimation with a single camera without IR illumination	claim
33	99	A covariance-based method for dynamic background subtraction	claim
34	96	Region-based active contours and sparse representations for texture segmentation	claim
35	96	A computer vision based camera pedestal's vertical motion control	claim
36	95	Handwritten Chinese character recognition using Local Discriminant Projection with Prior Information	claim
37	94	Face recognition using Complete Fuzzy LDA	claim
38	93	Super-resolution from unregistered omnidirectional images	claim
39	93	Background subtraction technique based on chromaticity and intensity patterns	claim
40	91	View-invariant full-body gesture recognition from video	claim
41	90	Scale-invariant medial features based on gradient vector flow fields	claim
42	90	A corner strength based Fingerprint segmentation algorithm with dynamic thresholding	claim
43	90	3D face recognition with the average-half-face	claim
44	89	A supervised learning approach for imbalanced data sets	claim
45	88	A local descriptor for finding corresponding points in vector fields	claim
46	87	Extended Kalman filtering approach to stereo video stabilization	claim
47	87	Multi-class classification strategies for Fisher scores of gesture and sign sequences	claim
48	87	Towards estimation of dense disparities from stereo images containing large textureless regions
49	86	Face age estimation using patch-based hidden Markov model supervectors	claim
50	85	A practical method to reducing metal artifact for dental CT scanners	claim
51	85	Virtual focusing image synthesis for user-specified image region using camera array	claim
52	85	Multitask learning for EEG-based biometrics	claim
53	85	Combined visual attention model for video sequences	claim
54	85	Alternative similarity functions for graph kernels	claim
55	84	Feature selection for real-time image matching systems	claim
56	83	Continuous graph cuts for prior-based object segmentation	claim
57	82	Motherese detection based on segmental and supra-segmental features	claim
58	82	Using SIFT features in palmprint authentication	claim
59	82	Hybrid statistical-structural on-line Chinese character recognition with fuzzy inference system	claim
60	82	Pedestrian detection by modeling local convex shape features	claim
61	82	Recognition of blurred faces using Local Phase Quantization	claim
62	81	3D Shape Context and Distance Transform for action recognition	claim
63	80	Cellular automaton for ultra-fast watershed transform on GPU	claim
64	80	Towards estimation of dense disparities from stereo images containing large textureless regions	claim
65	79	Shape from self-calibration and Fast Marching Method	claim
66	78	Human motion recognition using Gaussian Processes classification	claim
67	78	An empirical comparison of graph-based dimensionality reduction algorithms on facial expression recognition tasks
68	77	Asymmetric Real Adaboost	claim
69	77	White-space models for offline Arabic handwriting recognition	claim
70	77	Wavelet-based salient points with scale information for classification	claim
71	76	Automatic face and facial features initialization for robust and accurate tracking	claim
72	76	Dynamic Oscillating Search algorithm for feature selection	claim
73	75	SVD based Kalman particle filter for robust visual tracking	claim
74	75	Symmetric segment-based stereo matching of motion blurred images with illumination variations	claim
75	75	Robust auto-calibration of a PTZ camera with non-overlapping FOV	claim
76	74	A machine learning based scheme for double JPEG compression detection	claim
77	74	Monocular video foreground segmentation system	claim
78	74	Spatio-temporal 3D pose estimation and tracking of human body parts using the Shape Flow algorithm	claim
79	74	Multi-cue collaborative kernel tracking with cross ratio invariant constraint	claim
80	73	A Hybrid PNN-GMM classification scheme for speech emotion recognition	claim
81	73	Block-diagonal form of distance matrix for region-based image retrieval	claim
82	73	Automatic generation of optimum classification cascades	claim
83	72	Texture segmentation benchmark	claim
84	72	A new algorithm for static camera foreground segmentation via active coutours and GMM	claim
85	72	Multiple kernel learning from sets of partially matching image features	claim
86	72	Efficient video text detection using edge features	claim
87	72	Efficient implementation of SVM for large class problems	claim
88	71	Background modelling in demanding situations with confidence measure	claim
89	71	Flexible object recognition in cluttered scenes using relative point distribution models	claim
90	71	Group action recognition in soccer videos	claim
91	71	Free-hand sketch grouping for video retrieval	claim
92	71	Edge-preserving unscented Kalman filter for speckle reduction	claim
93	71	A method of small object detection and tracking based on particle filters	claim
94	70	Improvements in hidden Markov model based Arabic OCR	claim
95	70	Video attention: Learning to detect a salient object sequence	claim
96	70	3D rotation invariant local binary patterns	claim
97	70	Convolutional Neural Network with embedded Fourier Transform for EEG classification	claim
98	70	Dual generative models for human motion estimation from an uncalibrated monocular camera	claim
99	70	Extraction of complex wavelet features for iris recognition	claim
100	70	Convex hull based approach for multi-oriented character recognition from graphical documents	claim
101	69	Contour grouping with shape manifold and distance transform	claim
102	69	Quantitative abdominal fat estimation using MRI	claim
103	69	The implication of data diversity for a classifier-free ensemble selection in random subspaces	claim
104	69	Hand motion expertise analysis using dynamic hierarchical activity modeling and isomap	claim
105	69	Word-wise Sinhala Tamil and English script identification using Gaussian kernel SVM	claim
106	69	Arterial Pulse Rate Variability analysis for diagnoses	claim
107	68	IR and visible face recognition using fusion of kernel based features	claim
108	68	Efficient background modeling through incremental Support Vector Data Description	claim
109	68	Prototype learning with margin-based conditional log-likelihood loss	claim
110	68	Incremental classification of invoice documents	claim
111	68	EK-SVD: Optimized dictionary design for sparse representations	claim
112	68	Phase based level set segmentation of blood vessels	claim
113	67	Geometric constraints on 2D action models for tracking human body	claim
114	67	Face recognition using anisotropic dual-tree complex wavelet packets	claim
115	67	A novel automatic seed point selection algorithm for breast ultrasound images	claim
116	67	Detecting global motion patterns in complex videos	claim
117	67	Harmonic mean for subspace selection	claim
118	67	Analysis of human behaviour in front of a target scene	claim
119	67	Multimodal biometrics management using adaptive score-level combination	claim
120	67	Illumination invariants based on Markov random fields	claim
121	67	Improving efficiency of fingerprint matching by minutiae indexing	claim
122	66	Semi-supervised learning by locally linear embedding in kernel space	claim
123	66	Pedestrian detection using boosted features over many frames	claim
124	66	Approximating a non-homogeneous HMM with Dynamic Spatial Dirichlet Process	claim
125	66	A 2D model for face superresolution	claim
126	66	Kernel Bisecting k-means clustering for SVM training sample reduction	claim
127	66	Multi-view face recognition by nonlinear tensor decomposition	claim
128	66	Removing salt-and-pepper noise from binary images of engineering drawings	claim
129	66	Denighting: Enhancement of nighttime images for a surveillance camera	claim
130	65	Very fast ellipse detection using GPU-based RHT	claim
131	65	Randomized trees for real-time one-step face detection and recognition	claim
132	65	Enforcing image consistency in multiple 3-D object modelling	claim
133	65	Adaptive pore model for fingerprint pore extraction	claim
134	65	An automatic cell segmentation method for differential interference contrast microscopy	claim
135	65	Estimating the number of people in crowded scenes by MID based foreground segmentation and head-shoulder detection	claim
136	64	Cervicographic image retrieval by spatial similarity of lesions	claim
137	64	SVMs, Gaussian mixtures, and their generative/discriminative fusion	claim
138	64	Image quality assessment with visual attention	claim
139	64	Robust estimation of foreground in surveillance videos by sparse error estimation	claim
140	63	A new radical-based approach to online handwritten Chinese character recognition	claim
141	63	Recognizing actions from still images	claim
142	63	Accelerating active contour algorithms with the Gradient Diffusion Field	claim
143	63	Graph cut based deformable model with statistical shape priors	claim
144	63	Monocular 3D tracking of multiple interacting targets	claim
145	63	Nonlocal morphological levelings by partial difference equations over weighted graphs	claim
146	62	Beyond partitions: Allowing overlapping groups in pairwise clustering	claim
147	62	3D face recognition using sparse spherical representations	claim
148	62	Filtering large fingerprint database for latent matching	claim
149	62	Joint visual vocabulary for animal classification	claim
150	62	Fast and precise kinematic skeleton extraction of 3D dynamic meshes	claim
151	62	Bag-of-visual-words models for adult image classification and filtering	claim
152	62	On using error bounds to optimize cost-sensitive multimodal biometric authentication	claim
153	61	Intuitive event modeling for personalized behavior monitoring	claim
154	61	Multiple view based 3D object classification using ensemble learning of local subspaces	claim
155	61	Hemorrhage slices detection in brain CT images	claim
156	61	Face super-resolution using 8-connected Markov Random Fields with embedded prior	claim
157	61	Facial expression analysis with facial expression deformation	claim
158	61	Boosted cannabis image recognition	claim
159	61	A hybrid approach to gender classification from face images	claim
160	61	Using covariance matrices for unsupervised texture segmentation	claim
161	61	Human action recognition with line and flow histograms	claim
162	61	Feature Fusion Hierarchies for gender classification	claim
163	60	Recognizing picture-taking environment from satellite images: A feasibility study	claim
164	60	Fast incremental learning for one-class support vector classifier using sample margin information	claim
165	60	Tracking of persons for video surveillance of unattended environments	claim
166	60	Efficient triangulation based on 3D Euclidean optimization	claim
167	60	Bregman distance to L1 regularized logistic regression	claim
168	60	Extraction of shoe-print patterns from impression evidence using Conditional Random Fields	claim
169	60	A contrario matching of SIFT-like descriptors	claim
170	60	Depth-based image mosaicing for both static and dynamic scenes	claim
171	60	Fake fingertip generation from a minutiae template	claim
172	59	Learning invariant region descriptor operators with genetic programming and the F-measure	claim
173	59	An extended version of the k-means method for overlapping clustering	claim
174	59	Road region estimation using a sequence of monocular images	claim
175	59	Evolving boundary detectors for natural images via Genetic Programming	claim
176	59	Segmentation by combining parametric optical flow with a color model	claim
177	59	Audio-visual event classification via spatial-temporal-audio words	claim
178	59	Video object segmentation based on graph cut with dynamic shape prior constraint	claim
179	59	A probabilistic Self-Organizing Map for facial recognition	claim
180	59	Feature selection for clustering with constraints using Jensen-Shannon divergence	claim
181	59	Synthesis of large realistic iris databases using patch-based sampling	claim
182	59	2D and 3D upper body tracking with one framework	claim
183	58	A discrete-time parallel update algorithm for distributed learning	claim
184	58	Automatic pose estimation of 3D facial models	claim
185	58	A discriminative semi-Markov model for robust scene text recognition	claim
186	58	Efficient automated method for image-based classification of microbial cells	claim
187	58	Incremental trajectory aggregation in video sequences	claim
188	58	Gaze tracking by Binocular Vision and LBP features	claim
189	58	Robust region-based background subtraction and shadow removing using color and gradient information	claim
190	57	A novel Gaussianized vector representation for natural scene categorization	claim
191	57	Combine hierarchical appearance statistics for accurate palmprint recognition	claim
192	57	An approach for dynamic combination of region and boundary information in segmentation	claim
193	57	An adaptive-PCA algorithm for reflectance estimation from color images	claim
194	57	Real-time abnormal motion detection in surveillance video	claim
195	57	Visual planes-based simultaneous localization and model refinement for augmented reality	claim
196	57	Indexing iris images	claim
197	57	Change detection based on adaptive Markov Random Fields	claim
198	57	An evaluation survey of binarization algorithms on historical documents	claim
199	57	Harris feature vector descriptor (HFVD)	claim
200	57	Tree-structure lossless coding using intervector angle	claim
201	56	Linear time recognition algorithms for topological invariants in 3D	claim
202	56	Solving quadratically constrained geometrical problems using lagrangian duality	claim
203	55	Robust modeling and recognition of hand gestures with dynamic Bayesian network	claim
204	55	View invariant object recognition	claim
205	55	Imaging biomarker analysis of rat mammary fat pads and glandular tissues in MRI images	claim
206	55	Separability of ternary Error-Correcting Output Codes	claim
207	55	Human tracking based on Soft Decision Feature and online real boosting	claim
208	55	Training sequential on-line boosting classifier for visual tracking	claim
209	55	Fingerprint indexing based on composite set of reduced SIFT features	claim
210	55	FCM-based orientation selection for competitive coding-based palmprint recognition	claim
211	55	Unsupervised image embedding using nonparametric statistics	claim
212	55	Head pose estimation: Classification or regression?	claim
213	55	Indefinite Kernel Fisher Discriminant	claim
214	55	A clustering algorithm combine the FCM algorithm with supervised learning normal mixture model	claim
215	55	Fast approximate kernel-based similarity search for image retrieval task	claim
216	54	Feature selection focused within error clusters	claim
217	54	A new HMM training and testing scheme	claim
218	54	A novel approach for the recognition of a wide Arabic handwritten word lexicon	claim
219	54	Growing neural gas for temporal clustering	claim
220	54	A phone-viseme dynamic Bayesian network for audio-visual automatic speech recognition	claim
221	54	Human activity analysis based on a torso-less representation	claim
222	54	Visualization of transitions of developing of hepatitis C virus-associated hepatocellular carcinoma	claim
223	54	FastWavelet-Based Visual Classification	claim
224	54	Image-based automatic detection of indoor scene events and interactive inquiry	claim
225	54	Transductive optimal component analysis	claim
226	54	An empirical study of facial components classification by integrating dimensionality reduction and clustering	claim
227	54	Correspondences of point sets using Particle Filters	claim
228	54	Fronto-normal gait incorporating accurate practical looming compensation	claim
229	54	Silhouette extraction based on iterative spatio-temporal local color transformation and graph-cut segmentation	claim
230	54	Phase diagram of a long bar under a higher-order active contour energy: Application to hydrographic network extraction from VHR satellite images	claim
231	54	3D object recognition by fast spherical correlation between combined view EGIs and PFT	claim
232	53	Detecting moving text in video using temporal information	claim
233	53	Rayleigh segmentation of the endocardium in ultrasound images	claim
234	53	Application of triphone clustering in acoustic modeling for continuous speech recognition in Bengali	claim
235	53	Superresolution and blind deconvolution of video	claim
236	53	Structure from Motion: Combining features correspondences and optical flow	claim
237	53	Improved novel view synthesis from depth image with large baseline	claim
238	53	Relative scale estimation between two camera motions	claim
239	53	A study of non-frontal-view facial expressions recognition	claim
240	53	Endmember detection using the Dirichlet process	claim
241	53	Generalized Nonlinear Discriminant Analysis	claim
242	53	Incremental learning in non-stationary environments with concept drift using a multiple classifier based approach	claim
243	53	Implicit active shape model employing boundary classifier	claim
244	53	Local shape features for object recognition	claim
245	53	How to make iris recognition easier?	claim
246	53	Fast and regularized local metric for query-based operations	claim
247	53	GPS coordinate estimation from calibrated cameras	claim
248	53	Beyond SVD: Sparse projections onto exemplar orthonormal bases for compact image representation	claim
249	53	Active contour detection of linear patterns in spectrogram images	claim
250	53	A novel segmentation algorithm for pulmonary nodule in chest radiograph	claim
251	53	Unsupervised mammograms segmentation	claim
252	53	Discriminative HMM training with GA for handwritten word recognition	claim
253	53	Integration of time-sequential range images for reconstruction of a high-resolution 3D shape	claim
254	53	Human activity recognition from frame's spatiotemporal representation	claim
255	53	A coordinate system for articulated 2D shape point correspondences	claim
256	53	Automatic bi-layer video segmentation based on sensor fusion	claim
257	52	Active query selection for semi-supervised clustering	claim
258	52	Complex background modeling and motion detection based on Texture Pattern Flow	claim
259	52	Incoherent motion detection using a time-series Gram matrix feature	claim
260	52	Affine moment invariants generated by automated solution of the equations	claim
261	52	Component-wise parameter smoothing for learning mixture models	claim
262	52	Object detection at multiple scales improves accuracy	claim
263	52	Affine invariant shape descriptors: The ICA-Fourier descriptor and the PCA-Fourier descriptor	claim
264	52	Combining shape-from-shading and stereo using Gaussian-Markov random fields	claim
265	52	Automatic road sign detection method based on Color Barycenters Hexagon model	claim
266	52	Tailoring text for automatic layouting of newspaper pages	claim
267	52	Automatic extraction of natural fracture traces from borehole images	claim
268	52	Multiscale competitive code for efficient palmprint recognition	claim
269	52	Simultaneous multi-modal registration of multiple images based on multi-dimensional joint phase moment distributions	claim
270	52	Every color chromakey	claim
271	52	Camera calibration for uneven terrains by observing pedestrians	claim
272	52	Sensor planning for PTZ cameras using the probability of camera overload	claim
273	52	Signature verification based on fusion of on-line and off-line kernels	claim
274	52	Improved document image binarization by using a combination of multiple binarization techniques and adapted edge information	claim
275	52	Estimating the readability of handwritten text - a Support Vector Regression based approach	claim
276	52	Back to the future: Robust foreground extraction with reversed-time background modeling	claim
277	52	A comparative evaluation of Average Face on holistic and local face recognition approaches	claim
278	52	Mobile Visual Aid Tools for Users with Visual Impairments	claim
279	52	Locality preserving multi-nominal logistic regression	claim
280	51	3D ear modeling and recognition from video sequences using shape from shading	claim
281	51	Query by table	claim
282	51	Temporal difference learning to detect unsafe system states	claim
283	51	Directional entropy feature for human detection	claim
284	51	Full body tracking-based human action recognition	claim
285	51	Motion capture data retrieval using an artist's doll	claim
286	51	Boosting local feature descriptors for automatic objects classification in traffic scene surveillance	claim
287	51	A new hierarchical approach in robust real-time image feature detection and matching	claim
288	51	A Hilbert warping method for camera-based finger-writing recognition	claim
289	51	Medical image registration using Phase-Only Correlation for distorted dental radiographs	claim
290	51	Automatic generation of HMM topology for sign language recognition	claim
291	51	On averaging face images for recognition under pose variations	claim
292	51	Quasi-Euclidean uncalibrated epipolar rectification	claim
293	51	Radical based fine trajectory HMMs of online handwritten characters	claim
294	51	Watershed framework to region-based image segmentation	claim
295	51	Image annotation refinement using semantic similarity correlation	claim
296	50	Frame-skipping tracking for single object with global motion detection	claim
297	50	Tracking of articulated pose and motion with a markerized grid suit	claim
298	50	Model-based visual self-localization using geometry and graphs	claim
299	50	Camera motion filtering and its applications	claim
300	50	People and luggage recognition in airport surveillance under real-time constraints	claim
301	50	Recovering audio-to-video synchronization by audiovisual correlation analysis	claim
302	50	Detecting and ordering salient regions for efficient browsing	claim
303	50	Layered object categorization	claim
304	50	Segmentation-free recognizer based on enhanced four plane feature for realistic Chinese handwriting	claim
305	50	A study of on-line handwritten chemical expressions recognition	claim
306	50	Thin layer tissue classification for electronic cleansing of CT colonography data	claim
307	50	Efficient user preference predictions using collaborative filtering	claim
308	50	Automated quantification of cell endocytosis using active contours and wavelets	claim
309	50	Classification by reflective convex hulls	claim
310	50	A new edge-based text verification approach for video	claim
311	50	Point-based digitally reconstructed radiograph	claim
312	50	Multiclass spectral clustering based on discriminant analysis	claim
313	50	An incremental method for accurate iris segmentation	claim
314	50	Locally invariant texture analysis from the topographic map	claim
315	49	Computing multiple view geometry in space-time from mutual projections of multiple cameras	claim
316	49	Towards mobile authentication using dynamic signature verification: Useful features and performance evaluation	claim
317	49	Approximation of salient contours in cluttered scenes	claim
318	49	Recognition of box-like objects by fusing cues of shape and edges	claim
319	49	Clustering by evidence accumulation on affinity propagation	claim
320	49	Recognition of books by verification and retraining	claim
321	49	Real-time camera position and posture estimation using a feature landmark database with priorities	claim
322	49	Making real games virtual: Tracking board game pieces	claim
323	49	Orientation and scale invariant mean shift using object mask-based kernel	claim
324	49	Fuzzy rule selection using Iterative Rule Learning for speech data classification	claim
325	49	Comparative analysis of registration based and registration free methods for cancelable fingerprint biometrics	claim
326	49	Fast super-resolution for license plate image reconstruction	claim
327	49	Kernel functions for robust 3D surface registration with spectral embeddings	claim
328	49	Collaborate ball and player trajectory extraction in broadcast soccer video	claim
329	49	Attention-based video reframing: Validation using eye-tracking	claim
330	49	Probabilistic tracking on Riemannian manifolds	claim
331	49	HOPS: Efficient region labeling using Higher Order Proxy Neighborhoods	claim
332	49	Combining visual and textual features for filtering spam emails	claim
333	49	Numerical analysis of Mahalanobis metric in vector space	claim
334	49	Fingerprint orientation analysis with topological modeling	claim
335	48	Counterfeit iris detection based on texture analysis	claim
336	48	Top down image segmentation using congealing and graph-cut	claim
337	48	Clothes-invariant gait identification using part-based adaptive weight control	claim
338	48	A novel efficient approach for audio segmentation	claim
339	48	Segmentation of overlapping/aggregating nuclei cells in biological images	claim
340	48	Describing texture directions with Von Mises distributions	claim
341	48	A novel stability quantification of detected interest points in scale-space	claim
342	48	Recovering Euclidean deformable models from stereo-motion	claim
343	48	Motion segmentation by consensus	claim
344	48	Extending depth of field by intrinsic mode image fusion	claim
345	48	Score based biometric template selection	claim
346	48	Integrated probability function on local mean distance for image recognition	claim
347	48	Pattern rejection strategies for the design of self-paced EEG-based Brain-Computer Interfaces	claim
348	48	Phase-adaptive image signal fusion using complex-valued wavelets	claim
349	48	Non-linear feature extraction by linear PCA using local kernel	claim
350	48	MDL patch correspondences on unlabeled images	claim
351	48	A Hidden Markov Model-based continuous gesture recognition system for hand motion trajectory	claim
352	48	Learning visual dictionaries and decision lists for object recognition	claim
353	48	Detecting trends in social bookmarking systems using a probabilistic generative model and smoothing	claim
354	48	Fast protein homology and fold detection with sparse spatial sample kernels	claim
355	48	Motion estimation approach based on dual-tree complex wavelets	claim
356	48	Force histograms computed in O(NlogN)	claim
357	48	Hybrid Layered Video Encoding for Mobile Internet-Based Computer Vision and Multimedia Applications	claim
358	48	Cone-restricted subspace methods	claim
359	48	Collaborative learning by boosting in distributed environments	claim
360	48	An adaptive scene description for activity analysis in surveillance video	claim
361	47	Scale invariant face recognition using probabilistic similarity measure	claim
362	47	Interactive feature visualization for image retrieval	claim
363	47	Video denoising via discrete regularization on graphs	claim
364	47	3D object localization based on occluding contour using STL CAD model	claim
365	47	Multiple classifier applied on predicting microsleep from speech	claim
366	47	Vector field resampling using local streamline approximation	claim
367	47	Relative advantage of touch over vision in the exploration of texture	claim
368	47	On efficient Viterbi decoding for hidden semi-Markov models	claim
369	47	Compact algorithm for strictly ML ellipse fitting	claim
370	47	A hierarchical model for the evaluation of biometric sample quality	claim
371	47	Learning motion patterns in crowded scenes using motion flow field	claim
372	47	Visual features with semantic combination using Bayesian network for a more effective image retrieval	claim
373	47	Generic scale-space process for handwriting documents analysis	claim
374	47	Double-edge-model based character stroke extraction from complex backgrounds	claim
375	47	Combining content and structure similarity for XML document classification using composite SVM kernels	claim
376	47	Challenging issues in iterative intelligent medical search	claim
377	47	Object-of-interest extraction by integrating stochastic inference with learnt active shape sketch	claim
378	47	Coring method for clustering a graph	claim
379	47	Image-based plant modeling by knowing leaves from their apexes	claim
380	47	Parametric video compression using appearance space	claim
381	47	A fast revised simplex method for SVM training	claim
382	47	An approximate algorithm for median graph computation using graph embedding	claim
383	47	Nonlocal graph regularization for image colorization	claim
384	47	Probabilistic clustering by random swap algorithm	claim
385	47	A class-selective rejection scheme based on blockwise similarity of typicality degrees	claim
386	47	Direct 3-D shape recovery from image sequence based on multi-scale Bayesian network	claim
387	47	Object recognition using graph spectral invariants	claim
388	46	Unsupervised dynamic texture segmentation using local spatiotemporal descriptors	claim
389	46	Spam filtering with several novel bayesian classifiers	claim
390	46	Dyslexia diagnostics by 3D texture analysis of cerebral white matter gyrifications	claim
391	46	Context aware privacy in visual surveillance	claim
392	46	Shot boundary detection using co-occurrence of global motion in video stream	claim
393	46	Online recognition of handwritten mathematical expressions with support for matrices	claim
394	46	Segmentation robust to the vignette effect for machine vision systems	claim
395	46	Merging maps of multiple robots	claim
396	46	Weakly supervised learning using proportion-based information: An application to fisheries acoustics	claim
397	46	Local Regularized Least-Square Dimensionality Reduction	claim
398	46	On-line boosted cascade for object detection	claim
399	46	Semantic grouping of visual features	claim
400	46	Partial closure-based constrained clustering with order ranking	claim
401	46	Similarity-based matching for face authentication	claim
402	46	Birkhoff polytopes, heat kernels and graph complexity	claim
403	46	A least square kernel machine with box constraints	claim
404	46	Spatio-temporal patches for night background modeling by subspace learning	claim
405	46	NorMaL: Non-compact Markovian Likelihood for change detection	claim
406	46	A study of semi-tied covariance modeling for online handwritten Chinese character recognition	claim
407	46	Variance estimation for two-class and multi-class ROC analysis using operating point averaging	claim
408	46	Clip retrieval using multi-modal biometrics in meeting archives	claim
409	46	Recognition of multiple drivers' emotional state	claim
410	46	Violence classification based on shape variations from multiple views	claim
411	46	Moving object segmentation using the 9/7-10/8 dual-tree complex filter bank	claim
412	46	Kernel oriented discriminant analysis for speaker-independent phoneme spaces	claim
413	46	The Fourier Analysis of 2DT movement with particular reference to hand gesture recognition	claim
414	46	Bilateral symmetry of object silhouettes under perspective projection	claim
415	45	On edge structure based adaptive observation model for facial feature tracking	claim
416	45	Script identification of camera-based images	claim
417	45	Color face recognition based on 2DPCA	claim
418	45	Unsupervised categorization of heterogeneous text images based on fractals	claim
419	45	Robust tracking of spatial related components	claim
420	45	Practical pure pan and pure tilt camera calibration	claim
421	45	A robust front page detection algorithm for large periodical collections	claim
422	45	Video caption duration extraction	claim
423	45	Distance transformation, reverse distance transformation and discrete medial axis on toric spaces	claim
424	45	Ballot mark detection	claim
425	45	Learning weighted distances for relevance feedback in image retrieval	claim
426	45	A feature selection algorithm for handwritten character recognition	claim
427	45	Topological structure-based alignment for fingerprint Fuzzy Vault	claim
428	45	Adaptive semantic Bayesian framework for image attention	claim
429	45	Manifold denoising with Gaussian Process Latent Variable Models	claim
430	45	A new approach to 3D shape recovery of local planar surface patches from shift-variant blurred images	claim
431	45	Group-based meta-classification	claim
432	45	Switching local and covariance matching for efficient object tracking	claim
433	45	Directionality measurement and illumination estimation of 3D surface textures by using mojette transform	claim
434	45	Analytical method for MGRF Potts model parameter estimation	claim
435	45	Uncertainty minimization in multi-sensor localization systems using model selection theory	claim
436	45	Using web search engines to improve text recognition	claim
437	45	Identification of phosphorylation sites using a hybrid classifier ensemble approach	claim
438	45	Time-series clustering by approximate prototypes	claim
439	45	An online polygonal approximation of digital signals and curves with Dynamic Programming algorithm	claim
440	45	Variational Maximum A Posteriori model similarity and dissimilarity matching	claim
441	45	Pose sentences: A new representation for action recognition using sequence of pose words	claim
442	45	Geodesic K-means clustering	claim
443	45	Robust decomposition of a digital curve into convex and concave parts	claim
444	44	Background variability modeling for statistical layout analysis	claim
445	44	Scribble-a-Secret: Similarity-based password authentication using sketches	claim
446	44	Online adaptive clustering in a decision tree framework	claim
447	44	Collaborative and content-based image labeling	claim
448	44	A performance controllable octree construction method	claim
449	44	Trajectories normalization for viewpoint invariant gait recognition	claim
450	44	MDL region-based image registration	claim
451	44	A probabilistic approach for tracking fibers	claim
452	44	Exploiting qualitative domain knowledge for learning Bayesian network parameters with incomplete data	claim
453	44	Usage of needle maps and shadows to overcome depth edges in depth map reconstruction	claim
454	44	Resolution enhancement for binocular stereo	claim
455	44	The polar distance transform by fast-marching	claim
456	44	SIFT features for object recognition and tracking within the IVSEE system	claim
457	44	Monocular multi-human detection using Augmented Histograms of Oriented Gradients	claim
458	44	Interactive labeling of facial action units	claim
459	44	Modulation-domain particle filter for template tracking	claim
460	44	Grading nuclear pleomorphism on histological micrographs	claim
461	44	Utilizing non-uniform cost learning for active control of inter-class confusion	claim
462	43	Illumination invariant spatio-colorimetric normalization	claim
463	43	Tree-serial dynamic programming for image processing	claim
464	43	A cascade detector for text detection in natural scene images	claim
465	43	Wang Notation Tool: Layout independent representation of tables	claim
466	43	How much handwritten text is needed for text-independent writer verification and identification	claim
467	43	Fast and automatic reconstruction of structured illumination microscopy images with multiscale products	claim
468	43	A method of feature selection using contribution ratio based on boosting	claim
469	43	Linear discriminant analysis for data with subcluster structure	claim
470	43	Fast model selection for MaxMinOver-based training of support vector machines	claim
471	43	Automatic video annotation with adaptive number of key words
472	43	Preceding car tracking using belief functions and a particle filter	claim
473	43	Shape-based matching of heart sounds	claim
474	43	A practical palmprint recognition algorithm using phase information	claim
475	42	Registration by using a pseudo color attribute	claim
476	42	Structural poisson mixtures for classification of documents	claim
477	42	Rapid signer adaptation for continuous sign language recognition using a combined approach of eigenvoices, MLLR, and MAP	claim
478	42	Specularity removal and relighting of 3D object model for virtual exhibition	claim
479	42	Combining hierarchical clusterings using min-transitive closure	claim
480	42	Automatic eye state recognition and closed-eye photo correction	claim
481	42	Face recognition using curvelet based PCA	claim
482	42	Graph-based classification for multiple observations of transformed patterns	claim
483	42	A Mixed Markov model for change detection in aerial photos with large time differences	claim
484	42	Combining local descriptors for 3D object recognition and categorization	claim
485	42	Probabilistic matching of line segments for their homography	claim
486	42	Asymmetric post-processing for stereo correspondence	claim
487	42	Unsupervised design of Artificial Neural Networks via multi-dimensional Particle Swarm Optimization	claim
488	42	On-line handwritten Kanji string recognition based on grammar description of character structures	claim
489	42	Image retrieval with graph kernel on regions	claim
490	42	A performance evaluation of filter design and coding schemes for palmprint recognition	claim
491	42	Boosting Gaussian mixture models via discriminant analysis	claim
492	42	Properties of the k-norm pruning algorithm for decision tree classifiers	claim
493	42	Dual clustering for categorization of action sequences	claim
494	42	Detection of digital processing of images through a realistic model of CCD noise	claim
495	42	Weighted solution path algorithm of support vector regression for abnormal data	claim
496	42	Lexicon-based offline recognition of Amharic words in unconstrained handwritten text	claim
497	42	Exact integral images at generic angles for 2D barcode detection	claim
498	42	Efficient image inner products applied to active appearance models	claim
499	42	Image segmentation towards natural clusters	claim
500	42	Figure-ground discrimination and distortion-tolerant recognition of color characters in scene images	claim
501	42	A new clustering approach based on graph partitioning for navigation patterns mining	claim
502	42	Incremental machine learning techniques for document layout understanding	claim
503	42	Dynamic filters selection for textual document image binarization	claim
504	42	Online handwritten Bangla character recognition using HMM	claim
505	42	Pose adaptive LDA based face recognition	claim
506	41	Constrained clustering by a novel graph-based distance transformation	claim
507	41	3D localization of partially buried object in unstructured environment	claim
508	41	A layered method of visibility resolving in depth image-based rendering	claim
509	41	Illuminant dependence of PCA, NMF and NTF in spectral color imaging	claim
510	41	Recursive structure and motion estimation from noisy uncalibrated video sequences	claim
511	41	Dynamic target classification in wireless sensor networks	claim
512	41	Text-tracking wearable camera system for visually-impaired people	claim
513	41	Unfolding warping for object recognition	claim
514	41	Redundant DWT based translation invariant wavelet feature extraction for face recognition	claim
515	41	An approach for video cut detection using bipartite graph matching as dissimilarity distance	claim
516	41	Understanding visual dictionaries via Maximum Mutual Information curves	claim
517	41	Detection of representative frames of a shot using multivariate Wald-Wolfowitz test	claim
518	41	Securing fingerprint template: Fuzzy vault with minutiae descriptors	claim
519	41	A geometric approach for accurate and efficient performance evaluation of layout analysis methods	claim
520	41	Medical image segmentation via min s-t cuts with sides constraints	claim
521	41	Human detection by searching in 3d space using camera and scene knowledge	claim
522	41	Microarray image analysis based on an evolutionary approach	claim
523	41	Semi-supervised marginal discriminant analysis based on QR decomposition	claim
524	41	Relevant pattern selection for subspace learning	claim
525	41	Robust extraction of 1D skeletons from grayscale 3D images	claim
526	41	Understanding vehicle motion via spatial integration of intensities	claim
527	41	Boosted complex moments for discriminant rotation invariant object recognition	claim
528	41	Hand modeling and tracking from voxel data: An integrated framework with automatic initialization	claim
529	41	Classification of perceived running fatigue in digital sports	claim
530	40	Hallucinating facial images and features	claim
531	40	People detection based on co-occurrence of appearance and spatiotemporal features	claim
532	40	Automatic geo-registration of maritime video feeds	claim
533	40	Fuzzy maximum scatter discriminant analysis and its application to face recognition	claim
534	40	Metal-dielectric object classification by polarization degree map	claim
535	40	Clustering of short commercial documents for the web	claim
536	40	Improving Bayesian Network parameter learning using constraints	claim
537	40	K-means clustering of proportional data using L1 distance	claim
538	40	Near real-time stereo based on effective cost aggregation	claim
539	40	Constrained piecewise linear approximation of digital curves	claim
540	40	Detecting shadows of moving vehicles based on HMM	claim
541	40	Applying similarity metrics to 3D acquisition in structured-light systems	claim
542	40	Noise robust voice detector for speaker recognition	claim
543	40	Simplified polynomial network classifier for handwritten character recognition	claim
544	40	On refining dissimilarity matrices for an improved NN learning	claim
545	40	Improvement on Mean Shift based tracking using second-order information	claim
546	40	Eigenspace interpolation for appearance-based object recognition	claim
547	40	Dynamic structure from motion based on nonlinear adaptive observers	claim
548	40	Image objects and multi-scale features for annotation detection	claim
549	40	A robust technique for text extraction in mixed-type binary documents	claim
550	40	Deformable template combining alignable and non-alignable sketches	claim
551	40	Rotation invariant local phase quantization for blur insensitive texture analysis	claim
552	40	Boosting performance for 2D Linear Discriminant Analysis via regression	claim
553	40	Selecting relevant features for human motion recognition	claim
554	40	Re-ranking of web image search results using a graph algorithm	claim
555	40	Real-time 3D tracking using multiple sample points	claim
556	40	New extensions of the 3-simplex for exterior orientation	claim
557	40	Improvement of feature matching in catadioptric images using gyroscope data	claim
558	39	A matrix alignment approach for link prediction	claim
559	39	Tracking features on a moving object using local image bases	claim
560	39	The structure analysis of ultra thin magnetic film images	claim
561	39	Fuzzy discriminant projections for facial expression recognition	claim
562	39	On segmentation evaluation metrics and region counts	claim
563	39	Unsupervised clustering using hyperclique pattern constraints	claim
564	39	Multivariate Laplace Filter: A heavy-tailed model for target tracking	claim
565	39	Semi-supervised learning on large complex simulations	claim
566	39	Template selection for on-line signature verification	claim
567	39	Tracking human body by using particle filter Gaussian process Markov-switching model	claim
568	39	Supervised learning of a generative model for edge-weighted graphs	claim
569	39	Biomapping: Privacy trustworthy biometrics using noninvertible and discriminable constructions	claim
570	39	3D model based vehicle localization by optimizing local gradient based fitness evaluation	claim
571	39	Clustering-based locally linear embedding	claim
572	39	Anomalous trajectory patterns detection	claim
573	39	Radon transform and Conformal Geometric Algebra with lines	claim
574	39	Learning a discriminative sparse tri-value transform	claim
575	39	Impulse noise removal by spectral clustering and regularization on graphs	claim
576	39	Illumination transition image: Parameter-based illumination estimation and re-rendering	claim
577	39	Real time appearance based hand tracking	claim
578	39	Probabilistic mixtures of differential profiles for shape recognition	claim
579	38	Use of band ratioing for building illumination independent texture classification systems	claim
580	38	Image transformation for object tracking in high-resolution video	claim
581	38	Information-based gaze control adaptation to scene context for mobile robots	claim
582	38	A novel robust kernel for appearance-based learning	claim
583	38	On the scalability of robot localization using high-dimensional features	claim
584	38	Object boundary extraction using Active B-Snake Model	claim
585	38	Feature selection combining genetic algorithm and Adaboost classifiers	claim
586	38	A novel 3-D motion estimation approach to virtual viewpoint control	claim
587	38	Optimal feature weighting for the discrete HMM	claim
588	38	On-line novelty detection using the Kalman filter and extreme value theory	claim
589	38	A new spatial perceptual mask for image watermarking	claim
590	38	Detection of Atrial Fibrillation using model-based ECG analysis	claim
591	38	An adaptive Monte Carlo approach to nonlinear image denoising	claim
592	38	Layered shape matching and registration: Stochastic sampling with hierarchical graph representation	claim
593	38	Robust trajectory estimation of soccer players by using two cameras	claim
594	38	An improved mean-shift tracker with kernel prediction and scale optimisation targeting for low-frame-rate video tracking	claim
595	38	Generalized Chebyshev Kernels for Support Vector Classification	claim
596	38	Joint segmentation and registration of elastically deformable objects	claim
597	37	Finite element modeling of facial deformation in videos for computing strain pattern	claim
598	37	Multifractality in arterial pulse	claim
599	37	Manifold optimisation for motion factorisation	claim
600	37	RANSAC-SVM for large-scale datasets	claim
601	37	Contour registration and corresponding point selection for dorsal fin recognition	claim
602	37	Computer-aided grading of lymphangioleiomyomatosis (LAM) using HRCT	claim
603	37	An interactive scene annotation tool for video surveillance	claim
604	37	Scale-invariant density-based clustering initialization algorithm and its application	claim
605	37	Computational approaches for real-time extraction of soft biometrics	claim
606	37	Effective features based on normal linear structures for detecting microcalcifications in mammograms	claim
607	37	Pattern vectors from the Ihara zeta function	claim
608	37	Face image retrieval by using Haar features	claim
609	37	Hand posture recognition with co-training	claim
610	37	Tile-based image visual codeword extraction for efficient indexing and retrieval	claim
611	37	Gene function prediction using protein domain probability and hierarchical Gene Ontology information	claim
612	37	Feature Extraction base on Local Maximum Margin Criterion	claim
613	37	Investigating the separability of features from different views for gait based gender classification	claim
614	37	Preliminary approach on synthetic data sets generation based on class separability measure	claim
615	37	Segmentation of periodically moving objects	claim
616	37	Improving digital ink interpretation through expected type prediction and dynamic dispatch	claim
617	37	Learning vector quantization with local subspace classifier	claim
618	37	A new multiobjective simulated annealing based clustering technique using stability and symmetry	claim
619	37	Regular texture removal for video stabilization	claim
620	37	Prior-updating ensemble learning for discrete HMM	claim
621	37	Ridge Regression for Two Dimensional Locality Preserving Projection	claim
622	37	Using an artificial imagination for texture retrieval	claim
623	37	Pre-extracting method for SVM classification based on the non-parametric K-NN rule	claim
624	37	Nonparametric Bayesian attentive video analysis	claim
625	37	Reducing noise and redundancy in registered range data for planar surface extraction	claim
626	37	Linear representation of discrete surfaces in 3D	claim
627	37	Enhanced speaker recognition based on intra-modal fusion and accent modeling	claim
628	37	Action recognition based on homography constraints	claim
629	37	Lennard-Jones force field for Geometric Active Contour	claim
630	37	Generative models for fingerprint individuality using ridge models	claim
631	36	Behaviour based particle filtering for human articulated motion tracking	claim
632	36	Robust recognition of 1-D barcodes using camera phones	claim
633	36	Comparison of Particle Swarm Optimization and Genetic Algorithm for HMM training	claim
634	36	Application of the wrapper framework for image object detection	claim
635	36	Multilinear analysis based on image texture for face recognition	claim
636	36	Integrating minutiae based fingerprint matching with local mutual information	claim
637	36	Matching images more efficiently with local descriptors	claim
638	36	Incremental clustering via nonnegative matrix factorization	claim
639	36	A factorization algorithm for trifocal tensor estimation	claim
640	36	Neural net vector quantizers for discrete HMM-based on-line handwritten whiteboard-note recognition	claim
641	36	Reversible binary image data hiding by run-length histogram modification	claim
642	36	Weightlessness feature - a novel feature for single tri-axial accelerometer based activity recognition	claim
643	36	Regional motion patterns for the Left Ventricle function assessment	claim
644	36	Embedding HMM's-based models in a Euclidean space: The topological hidden Markov models	claim
645	36	Determination of optimal metabolic pathways through a new learning algorithm	claim
646	36	A fast image retrieval system using index lookup table on mobile device	claim
647	36	Fast multiple instance learning via L1, 2 logistic regression	claim
648	36	Knowledge based cluster ensemble for 3D head model classification	claim
649	36	Using collaborative learning for image contrast enhancement	claim
650	35	A network intrusion detection method using independent component analysis	claim
651	35	Regression with interval output values	claim
652	35	Static text region detection in video sequences using color and orientation consistencies	claim
653	35	Image segmentation by convex quadratic programming	claim
654	35	Ranking the local invariant features for the robust visual saliencies	claim
655	35	Application of graph coloring in physical layout segmentation	claim
656	35	An efficient gradient computation approach to discriminative fusion optimization in semantic concept detection	claim
657	35	Confidence rated boosting algorithm for generic object detection	claim
658	35	Texture classification with minimal training images	claim
659	35	Early recognition of sequential patterns by classifier combination	claim
660	35	Ancient document analysis based on text line extraction	claim
661	35	An experimental study of graph classification using prototype selection	claim
662	35	C1 units for scene classification	claim
663	35	Tracking of Arabidopsis thaliana root cells in time-lapse microscopy	claim
664	35	Establishing point correspondence using multidirectional binary pattern for face recognition	claim
665	35	Fractal-based system for Arabic/Latin, printed/handwritten script identification	claim
666	35	Generalized Gaussian distributions for sequential data classification	claim
667	35	Bagging very weak learners with lazy local learning	claim
668	35	Calibration of a structured light system by observing planar object from unknown viewpoints	claim
669	35	Object localization using affine invariant substructure constraints	claim
670	35	Online personal identification in night using multiple face representations	claim
671	35	Control and recognition on a humanoid head with cameras having different field of view	claim
672	35	Non-Abelian invariant feature detection	claim
673	35	A symbol graph based handwritten math expression recognition	claim
674	34	Computer graphics identification using genetic algorithm	claim
675	34	Semi-supervised feature selection under logistic I-RELIEF framework	claim
676	34	Robust outdoor text detection using text intensity and shape features	claim
677	34	Learning polynomial function based neutral-emotion GMM transformation for emotional speaker recognition	claim
678	34	Text detection from scene images using sparse representation	claim
679	34	Estimating the number of people in a video sequence via geometrical model	claim
680	34	Human reappearance detection based on on-line learning	claim
681	34	Fast and robust image identification	claim
682	34	Adaptive selection of non-target cluster centers for K-means tracker	claim
683	34	A non-cooperative long-range biometric system for maritime surveillance	claim
684	34	Remote multimodal biometric authentication using bit priority-based fragile watermarking	claim
685	34	A novel orientation free method for online unconstrained cursive handwritten chinese word recognition	claim
686	34	Dynamic score combination of binary experts	claim
687	34	Tracking a firefly - a stable likelihood estimation for variable appearance object tracking	claim
688	34	Effective shrinkage of large multi-class linear svm models for text categorization	claim
689	34	Large margin AR model for time series classification	claim
690	34	A bottom-up, view-point invariant human detector	claim
691	34	Sitting posture analysis by pressure sensors	claim
692	34	Spatially-variant morphological operations on binary images based on the polar distance transform	claim
693	34	Robust relative pose estimation with integrated cheirality constraint	claim
694	34	A fuzzy c-means algorithm using a correlation metrics and gene ontology	claim
695	34	Bayesian sequential face detection with automatic re-initialization	claim
696	34	Stop word detection in compressed textual images: An experiment on indic script documents	claim
697	34	Detecting hubs and quasi cliques in scale-free networks	claim
698	34	Generalized criteria for uniqueness of Gibbs measures	claim
699	34	Real-time accurate optical flow-based motion sensor	claim
700	34	Subject-independent brain computer interface through boosting	claim
701	33	Learning combined similarity measures from user data for image retrieval	claim
702	33	A device enhancing and denoising algorithm for X-ray cardiac fluoroscopy	claim
703	33	Face recognition based on LBP and orthogonal rank-one tensor projections	claim
704	33	Classification by bagged consistent itemset rules	claim
705	33	Refining PTZ camera calibration	claim
706	33	Point-of-interest detection for range data	claim
707	33	MCS-based balancing techniques for skewed classes: An empirical comparison	claim
708	33	Morphological source separation for particle tracking in complex biological environments	claim
709	33	Semi-supervised discriminant analysis based on UDP regularization	claim
710	33	Iris localization based on multi-resolution analysis	claim
711	33	Robust estimation for sparse data	claim
712	33	Intelligence computing approach for seizure detection based on intracranial electroencephalogram (IEEG)	claim
713	33	Improving Gaussian processes classification by spectral data reorganizing	claim
714	33	Image sampling for localization using entropy	claim
715	33	Wire detection in low-altitude, urban, and low-quality video frames	claim
716	33	Multimodal biometrics fusion using Correlation Filter Bank	claim
717	33	Target tracking using mean-shift and affine structure	claim
718	33	Parameter-based reduction of Gaussian mixture models with a variational-Bayes approach	claim
719	33	Estimating 3D fibre orientation in volume images	claim
720	33	Model-based combined tracking and resolution enhancement	claim
721	33	Improved percolation-based method for crack detection in concrete surface images	claim
722	32	The projective equation of a circle and its application in camera calibration	claim
723	32	A Bayesian Local Binary Pattern texture descriptor	claim
724	32	Categorization using semi-supervised clustering	claim
725	32	A new objective function for sequence labeling	claim
726	32	Efficient MRF approach to document image enhancement	claim
727	32	A probabilistic model for classifying segmented images	claim
728	32	Toward an interactive device for quick news story browsing	claim
729	32	Optimal feature weighting for the continuous HMM	claim
730	32	Incremental nested partition method	claim
731	32	Spectral aggregation for clustering ensemble	claim
732	32	Layer-based binarization for textual images	claim
733	32	On the gaussian distribution of strings	claim
734	32	An evaluation of bi-modal facial appearance+facial expression face biometrics	claim
735	32	Facial expression recognition from near-infrared video sequences	claim
736	32	Entropic thresholding based on gray-level spatial correlation histogram	claim
737	32	Detecting queues at vending machines: A statistical layered approach	claim
738	32	RUSBoost: Improving classification performance when training data is skewed	claim
739	32	A scene-based video watermarking technique using SVMs	claim
740	32	Augment document image binarization by learning	claim
741	31	Online anomal movement detection based on unsupervised incremental learning	claim
742	31	A method for removing cyclic artefacts in discrete tomography using latin squares	claim
743	31	An improvement on learning with local and global consistency	claim
744	31	Tracking across non-overlapping views via geometry	claim
745	31	Finding the splitting vector for image resolution up-conversion	claim
746	31	A stochastic nearest neighbor character prototype approach for online writer identification	claim
747	31	Efficient geometric matching with higher-order features	claim
748	31	Multi-script handwriting recognition with N-streams low level features	claim
749	31	Watershed-guided inpainting for image magnification	claim
750	31	Automatic coefficient selection in Weighted Maximum Margin Criterion	claim
751	31	An example based image retrieval system for the TRACE repository	claim
752	31	Indexing and retrieving cursive documents without recognition	claim
753	31	Bayesian classification for the Statistical Hough transform	claim
754	31	Qualitative analysis of spatio-temporal event detectors	claim
755	31	On-line signature verification by using most discriminating points	claim
756	31	Quantitative analysis of Iaido proficiency by using motion data	claim
757	31	Verification of human faces using predicted eigenvalues	claim
758	31	Help-training for semi-supervised discriminative classifiers. Application to SVM	claim
759	30	Intruders pattern identification	claim
760	30	A novel validity measure for clusters of arbitrary shapes and densities	claim
761	30	A study of change detection from satellite images using joint intensity histogram	claim
762	30	Image analysis approach for identification of renal transplant rejection	claim
763	30	Robust indoor activity recognition via boosting	claim
764	30	An MCMC-based particle filter for multiple person tracking	claim
765	30	3D ordinal constraint in spatial configuration for robust scene recognition	claim
766	30	Detecting changes in multilayered orthoimages with spatiotemporal texture blocks	claim
767	30	Convenient reconstruction of natural plants by images	claim
768	30	Film shot classification using directing semantics	claim
769	30	Novel image feature alphabets for object recognition	claim
770	30	Fingerprint alignment using special ridges	claim
771	30	Efficient and accurate subpixel path based stereo matching	claim
772	30	Real-time update of 3D deformable models for computer aided liver surgery	claim
773	30	Graph drawing using quantum commute time	claim
774	30	Tongue line extraction	claim
775	30	Scale-invariant region-based hierarchical imagematching	claim
776	30	Video summarization with supervised learning	claim
777	30	GA based feature generation for training cascade object detector	claim
778	30	A colour text/graphics separation based on a graph representation	claim
779	30	On second order operators and quadratic operators	claim
780	30	A statistical signature for automatic dialogue classification	claim
781	30	A new courtesy amount recognition module of a Check Reading System	claim
782	30	A self-organized approach for unsupervised fault detection in multiple systems	claim
783	30	A novel method for real-time multiple moving targets detection from moving IR camera	claim
784	30	Probabilistic Diffusion Classifiers for Object Detection	claim
785	29	Adaptive context recognition based on audio signal	claim
786	29	A new method to obtain the shift-table in Boyer-Moore's string matching algorithm	claim
787	29	Unsupervised writer style adaptation for handwritten word spotting	claim
788	29	Depth recovery using defocus blur at infinity	claim
789	29	Uncertainty based classification fusion - a soft-biometrics test case	claim
790	29	Ear recognition using LLE and IDLLE algorithm	claim
791	29	Measuring skin reflectance parameters	claim
792	29	Classification method for microarray probe selection using sequence, thermodynamics and secondary structure parameters	claim
793	29	Monte Carlo subspace method: An incremental approach to high-dimensional data classification	claim
794	29	Robust shape normalization based on implicit representations	claim
795	29	Automated stroke ending analysis for drawing tool classification	claim
796	28	Human activities: Handling uncertainties using fuzzy time intervals	claim
797	28	Adaptive asymmetrical SVM and genetic algorithms based iris recognition	claim
798	28	A non-parametric scale-based corner detector	claim
799	28	Image inpainting using wavelet-based inter- and intra-scale dependency	claim
800	28	A cryptosystem based on palmprint feature	claim
801	28	Multi-stage branch-and-bound for maximum variance disparity clustering	claim
802	28	Discriminative estimation of 3D human pose using Gaussian processes	claim
803	28	Regularized discriminant analysis for transformation-invariant object recognition	claim
804	28	Smile, you're on identity camera	claim
805	28	Identification and pose under severe occlusion in range images	claim
806	28	A hypergraph-based approach to affine parameters estimation	claim
807	28	Hierarchical estimation for adaptive visual tracking	claim
808	28	IBR-based free-viewpoint imaging of a complex scene using few cameras	claim
809	27	Adaptive Laplacian eigenfunctions as bases for regression analysis	claim
810	27	Efficient tensor based face recognition	claim
811	27	Non-rigid image registration based on the globally optimized correspondences	claim
812	27	Confidence-based cost modulation for stereo matching	claim
813	27	Gesture recognition using sparse code of Hierarchical SOM	claim
814	27	Navigation using a spherical camera	claim
815	27	Multiscan-based map optimizer for RFID map-building with low-accuracy measurements	claim
816	27	Lie group distance based generic 3-d vehicle classification	claim
817	27	Error-Correcting output coding for chagasic patients characterization	claim
818	27	Representative feature chain for single gallery image face recognition	claim
819	27	Impact of feature correlations on separation between bivariate normal distributions	claim
820	26	The lattice width and quasi-straightness in digital spaces	claim
821	26	Gender classification in two Emotional Speech databases	claim
822	26	Consistent and efficient sampler for geometric computation	claim
823	26	Analysis of efficient lip reading method for various languages	claim
824	26	Assembly of puzzles by connecting between blocks	claim
825	26	Vector valued regression for iron overload estimation	claim
826	26	Bag-of-features kernel eigen spaces for classification	claim
827	26	A variational inference based approach for image segmentation	claim
828	26	Adaptive nonstationary regression analysis	claim
829	26	Graph-based semi-supervised learning with redundant views	claim
830	26	A real-time accompaniment system based on sung voice recognition	claim
831	26	A new HMM for on-line character recognition using pen-direction and pen-coordinate features	claim
832	26	A uniformity criterion and algorithm for data clustering	claim
833	26	Detecting information-hiding in WAV audios	claim
834	25	HMM-based unusual motion detection without tracking	claim
835	25	A density-based approach for text extraction in images	claim
836	25	Support Vector Data Description for image categorization from Internet images	claim
837	25	Topologically correct surface reconstruction using alpha shapes and relations to ball-pivoting	claim
838	25	Stereo matching using random walks	claim
839	24	Video-based activity and movement pattern analysis in overnight sleep studies	claim
840	24	Effective scene matching with local feature representatives	claim
841	24	Detection of the intersection lines in multiplanar environments: Application to real-time estimation of the camera-scene geometry	claim
842	24	A framework for efficient correspondence using feature interrelations	claim
843	24	An affinity propagation based method for vector quantization codebook design	claim
844	24	Three related types of multi-value association patterns	claim
845	23	Non-dominated Sorting Evolution Strategy-based K-means clustering algorithm for accent classification	claim
846	23	Gender classification based on facial surface normals	claim
847	23	Combining motion and appearance for gender classification from video sequences	claim
848	22	On the selection of base prototypes for LAESA and TLAESA classifiers	claim
849	22	Facial feature estimation from the local structural diversity of skulls	claim
850	21	On the efficient minimization of convex surrogates in supervised learning	claim
851	21	Hybrid wavelet support vector classification of temporal bone abnormalities	claim
852	21	Document-zone classification using partial least squares and hybrid classifiers	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers