ICPR 2006 - PDF Preprint Papers

ICPR 2006 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-2006 Paper

click to vote

ICPR
2006
IEEE

824views computer vision» more ICPR 2006»

Learning-Based License Plate Detection Using Global and Local Features

2 years 3 months ago

Download www-staff.it.uts.edu.au

This paper proposes a license plate detection algorithm using both global statistical features and local Haar-like features. Classifiers using global statistical features are cons...

Huaifeng Zhang, Qiang Wu, Wenjing Jia, Xiangjian H...

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	824	Learning-Based License Plate Detection Using Global and Local Features	claim
2	803	Local Binary Pattern Descriptors for Dynamic Texture Recognition	claim
3	587	A Robust Split-and-Merge Text Segmentation Approach for Images	claim
4	320	Tone Mapping for HDR Image using Optimization A New Closed Form Solution	claim
5	315	Challenges for Data Mining in Distributed Sensor Networks	claim
6	255	Isomap Based on the Image Euclidean Distance	claim
7	252	Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure	claim
8	226	An Efficient Features - Based License Plate Localization Method	claim
9	186	Precision-recall operating characteristic (P-ROC) curves in imprecise environments	claim
10	144	An LBP-Based Active Contour Algorithm for Unsupervised Texture Segmentation	claim
11	141	Character Segmentation-by-Recognition Using Log-Gabor Filters	claim
12	126	A Higher-Order Active Contour Model for Tree Detection
13	124	Multi-orientation analysis by decomposing the structure tensor and clustering	claim
14	124	Bottom-Up Hierarchical Image Segmentation Using Region Competition and the Mumford-Shah Functional	claim
15	121	Real-Time Camera Tracking Using Known 3D Models and a Particle Filter	claim
16	120	Control Double Inverted Pendulum by Reinforcement Learning with Double CMAC Network	claim
17	109	Modelling Crowd Scenes for Event Detection	claim
18	107	Object Tracking Using Globally Coordinated Nonlinear Manifolds	claim
19	103	Object Predetection Based on Kernel Parametric Distribution Fitting
20	100	A New Structural Constraint and its Application in Wide Baseline Matching	claim
21	97	Non-Iterative Two-Dimensional Linear Discriminant Analysis	claim
22	95	Phoneme segmentation of speech	claim
23	95	YUV Correction for Multi-View Video Compression	claim
24	94	3-D Surface Moment Invariants	claim
25	91	Face Recognition Robust to Head Pose from One Sample Image	claim
26	90	An Omnidirectional Stereo Vision System Using a Single Camera	claim
27	90	Latent Layout Analysis for Discovering Objects in Images	claim
28	90	Robust Eye Detection under Active Infrared Illumination	claim
29	84	Finding Text in Natural Scenes by Figure-Ground Segmentation	claim
30	82	Adaptive Feature Integration for Segmentation of 3D Data by Unsupervised Density Estimation	claim
31	81	An Efficient Radical-Based Algorithm for Stroke-Order-Free Online Kanji Character Recognition	claim
32	80	Recognizing Facial Expressions by Tracking Feature Shapes	claim
33	79	A Hierarchical Object Recognition System Based on Multi-scale Principal Curvature Regions	claim
34	78	Multiple Camera Calibration with Bundled Optimization using Silhouette Geometry Constraints	claim
35	78	Using Evolution to Learn How to Perform Interest Point Detection	claim
36	78	Reconstruction of 3D Face Model from Single Shading Image Based on Anatomical Database	claim
37	77	A Convolution Edit Kernel for Error-tolerant Graph Matching	claim
38	76	Real-time Camera Pose and Focal Length Estimation	claim
39	76	3D Scene Reconstruction from Reflection Images in a Spherical Mirror	claim
40	75	Integrating EMD and Gradient for Generating Primal Sketch of Natural Images	claim
41	73	Structural flow smoothing for shape interpolation	claim
42	73	Detection-Assisted Initialization, Adaptation and Fusion of Body Region Trackers for Robust Multiperson Tracking	claim
43	72	Bayesian Imitation of Human Behavior in Interactive Computer Games	claim
44	72	Unusual Event Detection via Multi-camera Video Mining	claim
45	72	Automatic Hip Bone Segmentation Using Non-Rigid Registration	claim
46	72	Adaptive variational sinogram interpolation of sparsely sampled CT data	claim
47	71	Detecting Text Lines in Handwritten Documents	claim
48	71	Efficient, Simultaneous Detection of Multiple Object Classes	claim
49	70	Initialization Techniques for Segmentation with the Chan-Vese Model	claim
50	69	A Charged Geometric Model for Active Contours	claim
51	69	An Experimental Study on Automatic Face Gender Classification	claim
52	69	Flexible Text Recovery from Degraded Typewritten Historical Documents	claim
53	69	Shape-based Discrimination and Classification of Cortical Surfaces	claim
54	69	Adaptive Discriminant Projection for Content-based Image Retrieval	claim
55	69	Chaining Planar Homographies for Fast and Reliable 3D Plane Tracking	claim
56	69	Object Localization Using Input/Output Recursive Neural Networks	claim
57	69	Local Representation of 3D Free-Form Contours for Pose Estimation	claim
58	69	ICA-Based Clustering for Resolving Permutation Ambiguity in Frequency-Domain Convolutive Source Separation	claim
59	69	Efficient Visual Tracking by Probabilistic Fusion of Multiple Cues	claim
60	69	Multiscale Feature Extraction of Finger-Vein Patterns Based on Curvelets and Local Interconnection Structure Neural Network	claim
61	68	Combining Dichotomizers for MAP Field Classification	claim
62	68	Robust Pose Invariant Facial Feature Detection and Tracking in Real-Time	claim
63	68	An Improved Semi-Supervised Support Vector Machine Based Translation Algorithm for BCI Systems	claim
64	67	Bijective Image Registration using Thin-Plate Splines	claim
65	67	Hidden Markov Models for Optical Flow Analysis in Crowds	claim
66	67	Geodesic Curves for Analysis of Continuous Implicit Shapes	claim
67	67	Matching Interest Points Using Affine Invariant Concentric Circles	claim
68	66	Non-overlapping Distributed Tracking using Particle Filter	claim
69	66	Face Set Classification using Maximally Probable Mutual Modes	claim
70	66	New Experiments on ICP-Based 3D Face Recognition and Authentication	claim
71	66	Ethiopic Character Recognition Using Direction Field Tensor	claim
72	66	Motion Dependent Spatiotemporal Smoothing for Noise Reduction in Very Dim Light Image Sequences	claim
73	66	Automatic Texture Synthesis for Face Recognition from Single Views	claim
74	65	FAIR: Towards A New Feature for Affinely-Invariant Recognition	claim
75	65	Genus-Zero Shape Classification Using Spherical Normal Image	claim
76	64	A General Framework for Agglomerative Hierarchical Clustering Algorithms	claim
77	63	Accurate 3-D Motion Tracking with an Application to Super-Resolution	claim
78	63	Finding Rule Groups to Classify High Dimensional Gene Expression Datasets	claim
79	63	Classification of Segmented Regions in Brightfield Microscope Images	claim
80	62	Note on Feature Selection for Polyp Detection in CT Colonography	claim
81	62	A Pixel-wise Object Tracking Algorithm with Target and Background Sample	claim
82	62	Biometrics based Asymmetric Cryptosystem Design Using Modified Fuzzy Vault Scheme	claim
83	61	Nonparametric Background Generation	claim
84	61	Document Flattening through Grid Modeling and Regularization	claim
85	61	Efficient Topological Localization Using Orientation Adjacency Coherence Histograms	claim
86	60	Video Completion for Perspective Camera Under Constrained Motion	claim
87	60	Real Time Tracking for 3D Realistic Lip Animation	claim
88	60	Illumination Invariant Texture Retrieval	claim
89	60	A novel SVM Geometric Algorithm based on Reduced Convex Hulls	claim
90	60	Learning Policies for Efficiently Identifying Objects of Many Classes	claim
91	60	Calibrating Freely Moving Cameras	claim
92	60	Domain Based LDA and QDA	claim
93	60	Unsupervised Discriminant Projection Analysis for Feature Extraction	claim
94	60	Graph Matching using Commute Time Spanning Trees	claim
95	59	Human-Robot Interaction by Whole Body Gesture Spotting and Recognition	claim
96	59	A New Approach to Automated Retinal Vessel Segmentation Using Multiscale Analysis	claim
97	59	Dimensionality Reduction with Adaptive Kernels	claim
98	59	Word Extraction from On-Line Handwritten Text Lines	claim
99	59	Data Fusion for 3D Gestures Tracking using a Camera mounted on a Robot	claim
100	59	Fast Feature Extraction Approach for Multi-Dimension Feature Space Problems	claim
101	59	A Prototypes-Embedded Genetic K-means Algorithm	claim
102	59	A Person and Context Specific Approach for Skin Color Classification	claim
103	58	Selecting vantage objects for similarity indexing	claim
104	58	3D Object Digitization: Majority Interpolation and Marching Cubes	claim
105	58	Patch-Based Gabor Fisher Classifier for Face Recognition	claim
106	58	Subpixel Alignment of MRI Data Under Cartesian and Log-Polar Sampling	claim
107	58	Quality-based Score Level Fusion in Multibiometric Systems	claim
108	58	Event Recognition with Fragmented Object Tracks	claim
109	58	Unsupervised Segmentation Using Gabor Wavelets and Statistical Features in LIDAR Data Analysis	claim
110	57	Feature selection for linear support vector machines	claim
111	57	A Novel Segmentation and Recognition Algorithm for Chinese Handwritten Address Character Strings	claim
112	57	Weakly Supervised Learning on Pre-image Problem in Kernel Methods	claim
113	57	A probabilistic model with parsinomious representation for sensor fusion in recognizing activity in pervasive environment	claim
114	57	A Statistical Assembled Model for Segmentation of Entire 3D Vasculature	claim
115	56	Canonical Skeletons for Shape Matching	claim
116	56	A maximum margin discriminative learning algorithm for temporal signals	claim
117	56	Wavelet denoising of multicomponent images, using a Gaussian Scale Mixture model	claim
118	56	Hybrid Off-Line Cursive Handwriting Word Recognition	claim
119	56	Euclidean Reconstruction of Deformable Structure Using a Perspective Camera with Varying Intrinsic Parameters	claim
120	56	Evaluating Feature Importance for Object Classification in Visual Surveillance	claim
121	56	Ent-Boost: Boosting Using Entropy Measure for Robust Object Detection	claim
122	56	Atlas-based 3D-Shape Reconstruction from X-Ray Images	claim
123	55	Invariant Features for 3D-Data based on Group Integration using Directional Information and Spherical Harmonic Expansion	claim
124	55	ECOC-ONE: A Novel Coding and Decoding Strategy	claim
125	55	Emotion Recognition Based on Joint Visual and Audio Cues	claim
126	55	Basic Concepts For Testing The Torah Code Hypothesis	claim
127	55	Self-Calibration Using Constant Camera Motion	claim
128	55	Texture Segmentation Using Independent Component Analysis of Gabor Features	claim
129	54	A Coarse-to-Fine Strategy for Vehicle Motion Trajectory Clustering	claim
130	54	Image-Based Rendering of Synthetic Diffuse Objects in Natural Scenes	claim
131	54	Evaluation of 3D Facial Feature Selection for Individual Facial Model Identification	claim
132	54	Camera Text Recognition based on Perspective Invariants	claim
133	54	Computation of Rotation Local Invariant Features using the Integral Image for Real Time Object Detection	claim
134	54	Modification of the AdaBoost-based Detector for Partially Occluded Faces	claim
135	54	Automatic Sports Video Genre Classification using Pseudo-2D-HMM	claim
136	54	A Captcha Mechanism By Exchange Image Blocks	claim
137	54	Visual Servoing in Presence of Non-Rigid Motion	claim
138	53	Change detection in streetscapes from GPS coordinated omni-directional image sequences	claim
139	53	Combining Cepstral and Prosodic Features in Language Identification	claim
140	53	Automatic Alignment of High-Resolution NMR Spectra Using a Bayesian Estimation Approach	claim
141	53	Box-like Superquadric Recovery in Range Images by Fusing Region and Boundary Information	claim
142	53	Automatic Adjustment of Discriminant Adaptive Nearest Neighbor	claim
143	52	Robust Segmentation of Hidden Layers in Video Sequences	claim
144	52	Robust Image Registration Based on Markov-Gibbs Appearance Model	claim
145	52	Five-Point Motion Estimation Made Easy	claim
146	52	Car/Non-Car Classification in an Informative Sample Subspace	claim
147	52	Boosted Markov Chain Monte Carlo Data Association for Multiple Target Detection and Tracking	claim
148	52	A Novel Volumetric Shape from Silhouette Algorithm Based on a Centripetal Pentahedron Model	claim
149	52	Fast Dichotomic Multiple Search Algorithm for Shortest Cirular Path	claim
150	52	Camera Calibration from Two Shadow Trajectories	claim
151	52	Real-Time 3D Articulated Pose Tracking using Particle Filters Interacting through Belief Propagation	claim
152	52	Detection of presynaptic terminals on dendritic spines in double labeling confocal images	claim
153	52	Segmentation of Medical Images with Regional Inhomogeneities	claim
154	52	Extracting Lines in Noisy Image Using Directional Information	claim
155	52	Monocular Vision Based SLAM for Mobile Robots	claim
156	52	Biometric Identification of Mice	claim
157	52	Combining Generative and Discriminative Methods for Pixel Classification with Multi-Conditional Learning	claim
158	52	A Global Solution to the SFS Problem Using B-spline Surface and Simulated Annealing	claim
159	51	Local Behaviours Labelling for Content Based Video Copy Detection	claim
160	51	Simultaneous Inference of View and Body Pose using Torus Manifolds	claim
161	51	Texture-Constrained Shape Prediction for Mouth Contour Extraction and its State Estimation	claim
162	51	Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS	claim
163	51	Generic Detection of Multi-Part Objects	claim
164	51	Fast, Illumination Insensitive Face Detection Based on Multilinear Techniques and Curvature Features	claim
165	51	Object Localization Based on Directional Information: Case of 2D Raster Data	claim
166	51	Performance driven facial animation using illumination independent appearance-based tracking
167	51	OCR Fonts Revisited for Camera-Based Character Recognition	claim
168	51	Early Recognition and Prediction of Gestures	claim
169	51	Automatic Detection of Intestinal Juices in Wireless Capsule Video Endoscopy	claim
170	51	Defect detection in low-contrast glass substrates using anisotropic diffusion	claim
171	51	Multi-modal Sequential Monte Carlo for On-Line Hierarchical Graph Structure Estimation in Model-based Scene Interpretation	claim
172	51	Exploiting High Dimensional Video Features Using Layered Gaussian Mixture Models	claim
173	51	Tracking 3D Human Body using Particle Filter in Moving Monocular Camera	claim
174	51	Boosted Gabor Features Applied to Vehicle Detection	claim
175	51	Does EigenPalm work? A System and Evaluation Perspective	claim
176	51	Ancient Initial Letters Indexing	claim
177	51	Adaptative Markov Random Fields for Omnidirectional Vision	claim
178	50	Detecting Coarticulation in Sign Language using Conditional Random Fields	claim
179	50	Effective and Generic Structure from Motion using Angular Error	claim
180	50	Smoothing with Active Surfaces: A Multiphase Level Set Approach	claim
181	50	Radon space and Adaboost for Pose Estimation	claim
182	50	Efficient Search and Verification for Function Based Classification from Real Range Images	claim
183	50	Multi-Subset Selection for Keyword Extraction and Other Prototype Search Tasks Using Feature Selection Algorithms	claim
184	50	Activity Discovery from Surveillance Videos	claim
185	50	Recognizing Rotated Faces from Two Orthogonal Views in Mugshot Databases	claim
186	50	GMM-based SVM for face recognition	claim
187	50	A Combined Bayesian Markovian Approach for Behaviour Recognition	claim
188	50	Discriminative Descriptor-Based Observation Model for Visual Tracking	claim
189	50	Global-to-Local Non-Rigid Shape Registration	claim
190	50	Honeybees as an Intelligent based Approach for 3D Reconstruction	claim
191	50	Optimal Estimation of Perspective Camera Pose	claim
192	50	Feature selection based on the training set manipulation	claim
193	50	Lexicon-based Browsers for Searching in News Video Archives	claim
194	49	3D and Infrared Face Reconstruction from RGB data using Canonical Correlation Analysis	claim
195	49	Hybrid Kernel Machine Ensemble for Imbalanced Data Sets	claim
196	49	An integrated Monte Carlo data association framework for multi-object tracking	claim
197	49	Boosted Band Ratio Feature Selection for Hyperspectral Image Classification	claim
198	49	Planning of Multiple Camera Arrangement for Object Recognition in Parametric Eigenspace	claim
199	49	Gait Recognition Using Fractal Scale and Wavelet Moments	claim
200	49	Contour Encoding Based on Extraction of Key Points Using Wavelet Transform	claim
201	49	Empirical Study of Multi-scale Filter Banks for Object Categorization	claim
202	49	Compound Stochastic Models For Fingerprint Individuality	claim
203	49	Synthesizing Reflections of Inserted Objects	claim
204	49	A Ground Truth Correspondence Measure for Benchmarking	claim
205	49	Fast Linear Discriminant Analysis Using Binary Bases	claim
206	49	Using Specularities to Recover Multiple Light Sources in the Presence of Texture	claim
207	49	Estimating the Optimal Quantization Parameter in H.264	claim
208	48	An Empirical Model for Saturation and Capacity in Classifier Spaces	claim
209	48	Image Renaissance Using Discrete Optimization	claim
210	48	Comparative Analysis of Decision-level Fusion Algorithms for 3D Face Recognition	claim
211	48	Off-line Signature Verification based on the Modified Direction Feature	claim
212	48	Image Classification from Generalized Image Distance Features: Application to Detection of Interstitial Disease in Chest Radiogr	claim
213	48	Anomaly Detection for Video Surveillance Applications	claim
214	48	Robust Head Pose Estimation Using LGBP	claim
215	48	EBEM: An Entropy-based EM Algorithm for Gaussian Mixture Models	claim
216	48	String-Like Occluding Region Extraction for Background Restoration	claim
217	48	Adaptation to Walking Direction Changes for Gait Identification	claim
218	48	DTM Generation from LIDAR Data using Skewness Balancing	claim
219	48	Multi-User Natural Interaction System based on Real-Time Hand Tracking and Gesture Recognition	claim
220	48	Video Synchronization Based on Co-occurrence of Appearance Changes in Video Sequences	claim
221	48	A Comparison of Texture Features Based on SVM and SOM	claim
222	48	A Moving Object Tracked by A Mobile Robot with Real-Time Obstacles Avoidance Capacity	claim
223	48	A New Objective Function for Ensemble Selection in Random Subspaces	claim
224	48	Mixture of Support Vector Machines for HMM based Speech Recognition	claim
225	48	A Method for the Identification of Noisy Regions in Normalized Iris Images	claim
226	48	A Semi-supervised SVM for Manifold Learning	claim
227	48	Active Feature Models	claim
228	47	Image template matching using Mutual Information and NP-Windows	claim
229	47	Forest Extension of Error Correcting Output Codes and Boosted Landmarks	claim
230	47	Using texture-based symbolic features for medical image representation	claim
231	47	A Texture Based Matching Approach for Automated Assembly of Puzzles	claim
232	47	Motion Features from Lip Movement for Person Authentication	claim
233	47	Binocular Hand Tracking and Reconstruction Based on 2D Shape Matching	claim
234	47	Improving evidential quality of surveillance imagery through active face tracking	claim
235	47	Type-2 Fuzzy Markov Random Fields to Handwritten Character Recognition	claim
236	47	Protein Fold Recognition using a Structural Hidden Markov Model	claim
237	47	Fingerprint Matching Method Using Minutiae Clustering and Warping	claim
238	47	Robust Tracking of Multiple People in Crowds Using Laser Range Scanners	claim
239	46	A Novel Pattern Classification Scheme: Classwise Non-Principal Component Analysis (CNPCA)	claim
240	46	Fingerprint Matching Using Minutia Polygons	claim
241	46	Face Recognition by Combining Kernel Associative Memory and Gabor Transforms	claim
242	46	Learning Mixtures of Offline and Online features for Handwritten Stroke Recognition	claim
243	46	An Illumination Insensitive Representation for Face Verification in the Frequency Domain	claim
244	46	3D Object Digitization: Topology Preserving Reconstruction	claim
245	46	Online Learning of Discriminative Patterns from Unlimited Sequences of Candidates	claim
246	46	Fast Linear Feature Detection Using Multiple Directional Non-Maximum Suppression	claim
247	46	Multilinear Principal Component Analysis of Tensor Objects for Recognition	claim
248	46	Bayesian Feedback in Data Clustering	claim
249	46	Face Recognition Using Angular LDA and SVM Ensembles	claim
250	46	Tracking a Variable Number of Human Groups in Video Using Probability Hypothesis Density	claim
251	45	Rotation-Invariant Neoperceptron	claim
252	45	Minimum Enclosing and Maximum Excluding Machine for Pattern Description and Discrimination	claim
253	45	Trains of keypoints for 3D object recognition	claim
254	45	Fingerprint Reference Point Detection Based on Local Axial Symmetry	claim
255	45	Analysis of Ramp Discontinuity Model for Multiscale Image Segmentation	claim
256	45	Hippocampal Surface Analysis Using Spherical Harmonic Function Applied to Surface Conformal Mapping	claim
257	45	Simultaneous Image Denoising and Compression by Multiscale 2D Tensor Voting	claim
258	45	Multi-View Active Shape Model with Robust Parameter Estimation	claim
259	45	Classification of Team Behaviors in Sports Video Games	claim
260	45	Part-Based Probabilistic Point Matching	claim
261	45	Context Enhancement of Nighttime Surveillance by Image Fusion	claim
262	45	Gaussian Weighted Histogram Intersection for License Plate Classification	claim
263	45	Convex Quadratic Programming for Object Localization	claim
264	45	Bijective Image Registration using Thin-Plate Splines.	claim
265	45	A Trainable Similarity Measure for Image Classification	claim
266	45	A Model-based Approach for Rigid Object Recognition	claim
267	45	Initialization and System Modeling in 3-D Pose Tracking	claim
268	45	Graph-based transformation manifolds for invariant pattern recognition with kernel methods	claim
269	45	Affine Invariant Dynamic Time Warping and its Application to Online Rotated Handwriting Recognition	claim
270	44	Part-Based Multi-Frame Registration for Estimation of the Growth Of Cellular Networks in Plant Roots	claim
271	44	Fast Synthesis of Dynamic Colour Textures	claim
272	44	Combinatorial Surface Integration	claim
273	44	Learning Pairwise Similarity for Data Clustering	claim
274	44	Robust Local Scoring Function for Text-Independent Speaker Verification	claim
275	44	A Psychological Adaptive Model For Video Analysis	claim
276	44	A Template-Matching Approach for Protein Surface Clustering	claim
277	44	Uncertainties-driven Surface Morphing: The case of Photo-realistic Transitions between Facial Expressions	claim
278	44	Adaptive Weighting of Local Classifiers by Particle Filter	claim
279	44	Automatic Pose Recovery for High-Quality Textures Generation	claim
280	44	Robust Alignment of Transmission Electron Microscope Tilt Series	claim
281	44	Edge-preserving Simultaneous Joint Motion-Disparity Estimation	claim
282	44	A Non-Iterative Approach to Reconstruct Face Templates from Match Scores	claim
283	44	Identification of degraded traffic sign symbols by a generative learning method	claim
284	44	Detecting irregularities in regular patterns	claim
285	44	Extending the Depth of Field in a Compound-Eye Imaging System with Super-Resolution Reconstruction	claim
286	44	Fault Detection in Distributed Systems by Representative Subspace Mapping	claim
287	44	Enhancing Training Set for Face Detection	claim
288	44	Improving human activity detection by combining multi-dimensional motion descriptors with boosting	claim
289	44	Gender Recognition in Non Controlled Environments	claim
290	44	Class Separability in Spaces Reduced By Feature Selection	claim
291	44	A Viewpoint Invariant Approach for Crowd Counting	claim
292	44	Metric tree partitioning and Taylor approximation for fast support vector classification	claim
293	44	Part Based Human Tracking In A Multiple Cues Fusion Framework	claim
294	44	A Regression Model in TensorPCA Subspace for Face Image Super-resolution Reconstruction	claim
295	43	Gesture Detection in Low-Quality Video	claim
296	43	Fingerprint Image Enhancement Based on Skin Profile Approximation	claim
297	43	Competitive Mixtures of Simple Neurons	claim
298	43	Early feature stream integration versus decision level combination in a multiple classifier system for text line recognition	claim
299	43	Object and Scene Classification: what does a Supervised Approach Provide us?	claim
300	43	Image Categorization Using Local Probabilistic Descriptors	claim
301	43	Automatic Acquisition of Context Models and its Application to Video Surveillance	claim
302	43	Clustering-based multispectral band selection using mutual information	claim
303	43	Transformation Invariance in Hand Shape Recognition	claim
304	43	View Dependent Enhancement of the Dynamic Range of Video	claim
305	43	Real Time Limb Tracking with Adaptive Model Selection	claim
306	43	Detecting Rotational Symmetry Under Affine Projection	claim
307	43	A 'No Panacea Theorem' for Multiple Classifier Combination	claim
308	42	Efficient Gaussian Mixture for Speech Recognition	claim
309	42	Kalman Filtering for Robust Identification of Face Images with Varying Expressions and Lighting Conditions	claim
310	42	The Twin Towers Cluster in Torah Codes	claim
311	42	Switching Auxiliary Chains for Speech Recognition based on Dynamic Bayesian Networks	claim
312	42	Bagging Based Efficient Kernel Fisher Discriminant Analysis for Face Recognition	claim
313	42	Interacting Active Rectangles for Estimation of Intervertebral Disk Orientation	claim
314	42	Estimating the location of illuminants in realist master paintings Computer image analysis addresses a debate in art history of	claim
315	42	Perspective Symmetry Invariant and Its Applications	claim
316	42	Estimating Geospatial Trajectory of a Moving Camera	claim
317	42	Texture Image Retrieval Using Novel Non-separable Filter Banks Based on Centrally Symmetric Matrices	claim
318	42	Multi-layer Mosaics in the Presence of Motion and Depth Effects	claim
319	42	LIGHT: Local Invariant Generalized Hough Transform	claim
320	42	A Conditional Random Field Model for Video Super-resolution	claim
321	42	A new approach to the classification of mammographic masses and normal breast tissue	claim
322	42	Recovering Non-overlapping Network Topology Using Far-field Vehicle Tracking Data	claim
323	42	Planar Structure Based Registration of Multiple Range Images	claim
324	42	The Generalized Condensed Nearest Neighbor Rule as A Data Reduction Method	claim
325	42	On Kernel Selection in Relevance Vector Machines Using Stability Principle	claim
326	41	Volume Motion Template for View-Invariant Gesture Recognition	claim
327	41	Camera-Based Document Image Mosaicing	claim
328	41	Multimodal Registration using the Discrete Wavelet Frame Transform	claim
329	41	Line Detection and Texture Characterization of Network Patterns	claim
330	41	MONNET: Monitoring Pedestrians with a Network of Loosely-Coupled Cameras	claim
331	41	Style Quantification of Scanned Multi-source Digits	claim
332	41	Multiple Object Tracking Using Local PCA	claim
333	41	Segmentation and Probabilistic Registration of Articulated Body Models	claim
334	41	Evaluating Hierarchical Graph-based Segmentation	claim
335	41	Pen-Coordinate Information Modeling by SCPR-based HMM for On-line Japanese Handwriting Recognition	claim
336	41	Exact View-Dependent Visual Hulls	claim
337	41	Configuring Mixed Reality Environment	claim
338	41	Visible Edges Thresholding: a HVS based Approach	claim
339	41	Change detection using joint intensity histogram	claim
340	41	Space-time Analysis of Spherical Projection Image	claim
341	41	Real-Time Spherical Stereo	claim
342	41	Improving Face Recognition by Online Image Alignment	claim
343	41	Fast Dynamic Mosaicing and Person Following	claim
344	41	Audio-Visual Speaker Localization Using Graphical Models	claim
345	40	3D Segmentation by Maximally Stable Volumes (MSVs)	claim
346	40	Structural Matching Via Optimal Basis Graphs	claim
347	40	Fundamental Matrix Estimation via TIP - Transfer of Invariant Parameters	claim
348	40	Near-Duplicate Image Recognition and Content-based Image Retrieval using Adaptive Hierarchical Geometric Centroids	claim
349	40	Scene recovery from many randomly distributed single pixel cameras	claim
350	40	Detection of Fence Climbing from Monocular Video	claim
351	40	On Authorship Attribution via Markov Chains and Sequence Kernels	claim
352	40	Iterative Error Bound Minimisation for AAM Alignment	claim
353	40	LDV Remote Voice Acquisition and Enhancement	claim
354	40	A Split & Merge Approach to Metric-Topological Map-Building	claim
355	40	Estimation of Ball Route under Overlapping with Players and Lines in Soccer Video Image Sequence	claim
356	40	Motion-Based Handwriting Recognition for Mobile Interaction	claim
357	40	Exploiting the Geometry of Gene Expression Patterns for Unsupervised Learning	claim
358	40	Robust Recursive Learning for Foreground Region Detection in Videos with Quasi-Stationary Backgrounds	claim
359	40	A Hybrid, Recursive Algorithm for Clustering Expressed Sequence Tags in Chlamydomonas reinhardtii	claim
360	40	Sociometry Based Multiparty Audio Recordings Summarization	claim
361	40	Robust Detection of Region-Duplication Forgery in Digital Image	claim
362	40	Background Subtraction Based on a Robust Consensus Method	claim
363	40	Efficient Night Gait Recognition Based on Template Matching	claim
364	40	Superimposing 3D Virtual Objects using Markerless Tracking	claim
365	40	Automatic Surveying of Cutaneous Hemangiomas	claim
366	40	Vessel Segmentation in 2D-Projection Images Using a Supervised Linear Hysteresis Classifier	claim
367	39	Association of Sound to Motion in Video using Perceptual Organization	claim
368	39	A Robust Algorithm for Generalized Orthonormal Discriminant Vectors	claim
369	39	Approximation of Digital Curves using a Multi-Objective Genetic Algorithm	claim
370	39	Classifiers for Motion	claim
371	39	A New Data Selection Principle for Semi-Supervised Incremental Learning	claim
372	39	Linear model combining by optimizing the Area under the ROC curve	claim
373	39	A Unified Formulation of Invariant Point Pattern Matching	claim
374	39	Action Recognition in Broadcast Tennis Video	claim
375	39	Browsing graphics without prior knowledge	claim
376	39	HMM-based Human Action Recognition Using Multiview Image Sequences	claim
377	39	Physics-based Fusion of Multispectral Data for Improved Face Recognition	claim
378	39	Automatic Estimation of 3D Transformations using Skeletons for Object Alignment	claim
379	39	CAPTCHA Challenge Tradeoffs: Familiarity of Strings versus Degradation of Images	claim
380	39	A Verification Method for Viewpoint Invariant Sign Language Recognition	claim
381	39	Combining Fingerprint, Palmprint and Hand-Shape for User Authentication	claim
382	39	Shadow Detection by Integrating Multiple Features	claim
383	39	Audio Segmentation and Speaker Localization in Meeting Videos	claim
384	39	Robust Appearance-based Tracking using a sparse Bayesian classifier	claim
385	39	Onset Detection through Maximal Redundancy Detection	claim
386	39	Recover Writing Trajectory from Multiple Stroked Image Using Bidirectional Dynamic Search	claim
387	39	Machine Learning for Video Compression: Macroblock Mode Decision	claim
388	38	Face Recognition by Expression-Driven Sketch Graph Matching	claim
389	38	Supervised Image Classification by SOM Activity Map Comparison	claim
390	38	Image classification: Classifying distributions of visual features	claim
391	38	Pay Attention When Selecting Features	claim
392	38	Detecting Virulent Cells of Cryptococcus Neoformans Yeast: Clustering Experiments	claim
393	38	Testing The Torah Code Hypothesis: The Experimental Protocol	claim
394	38	Adaptive Step Size Window Matching for Detection	claim
395	38	A Target Dependent Colorspace for Robust Tracking	claim
396	38	An Oriented-Contour Point Based Voting Algorithm for Vehicle Type Classification	claim
397	38	Adaptive Binarization of Historical Document Images	claim
398	38	Efficient Region Based Indexing and Retrieval for Images with Elastic Bucket Tries	claim
399	38	Human Head Tracking in Three Dimensional Voxel Space	claim
400	38	Epipolar Geometry from Two Correspondences	claim
401	38	Automatic Detection of Song Changes in Music Mixes Using Stochastic Models	claim
402	38	Continuous Gesture Recognition using a Sparse Bayesian Classifier	claim
403	38	Embodied Proactive Human Interface "PICO-2"	claim
404	37	A face recognition system dealing with expression variant faces	claim
405	37	Removing Temporal Stationary Blur in Route Panoramas	claim
406	37	Vehicle Lateral Position Estimation Method Based on Matching of Top-View Images	claim
407	37	Unifying Background Models over Complex Audio using Entropy	claim
408	37	Direct Mapping of Visual Input to Motor Torques	claim
409	37	A Unified System for Segmentation and Tracking of Face and Hands in Sign Language Recognition	claim
410	37	Pores and Ridges: Fingerprint Matching Using Level 3 Features	claim
411	37	A Markovian Approach for Handwritten Document Segmentation	claim
412	37	A Maximum-Likelihood Approach to Symbolic Indirect Correlation	claim
413	37	A Novel Vision based Finger-writing Character Recognition System	claim
414	37	Variational Multigrid for Fast 3D Interpretation of Image Sequences	claim
415	37	Tensor Voting Accelerated by Graphics Processing Units (GPU)	claim
416	37	A Minimum Sphere Covering Approach to Pattern Classification	claim
417	37	ViSE: Visual Search Engine Using Multiple Networked Cameras	claim
418	37	An Anatomy of IrisCode for Precise Phase Representation	claim
419	37	Adaptive Processing of Face Emotion Tree Structures	claim
420	37	Matching 2D Shapes using their Symmetry Sets	claim
421	37	Object Detection in Video via Particle Filters	claim
422	36	Transforming Static CT in Gated PET/CT Studies to Multiple Respiratory Phases	claim
423	36	Texture Edge Detection using Multi-resolution Features and SOM	claim
424	36	Target Model Estimation using Particle Filters for Visual Servoing	claim
425	36	A fast binary-image comparison method with local-dissimilarity quantification	claim
426	36	Reconciling Landmarks and Level Sets	claim
427	36	Patterns of Co-Linear Equidistant Letter Sequences and Verses	claim
428	36	Scalable Representative Instance Selection and Ranking	claim
429	36	Gaussian mixture pdf in one-class classification: computing and utilizing confidence values	claim
430	36	Camera Motion Quantification and Alignment	claim
431	36	A fusion methodology based on Dempster-Shafer evidence theory for two biometric applications	claim
432	36	A Kernel-based Discrimination Framework for Solving Hypothesis Testing Problems with Application to Speaker Verification	claim
433	36	Multi-lingual Phoneme Recognition and Language Identification Using Phonotactic Information	claim
434	36	Learning Wormholes for Sparsely Labelled Clustering	claim
435	36	Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching	claim
436	36	The Hidden Birth Dates of Personalities of Genesis	claim
437	35	Nonlinear Shape and Appearance Models for Facial Expression Analysis and Synthesis	claim
438	35	Component Analysis of Torah Code Phrases	claim
439	35	Template Adaptation based Fingerprint Verification	claim
440	35	Measurement Function Design for Visual Tracking Applications	claim
441	35	Stroke Segmentation of Chinese Characters Using Markov Random Fields	claim
442	35	Image Classification from Generalized Image Distance Features: Application to Detection of Interstitial Disease in Chest Radiographs	claim
443	35	Robust 3D Head Tracking Using Camera Pose Estimation	claim
444	35	A New Approach for Fractal Image Compression on a Virtual Hexagonal Structure	claim
445	34	Layered Search Spaces for Accelerating Large Set Character Recognition	claim
446	34	Statistical Model for the Classification of the Wavelet Transforms of T-ray Pulses	claim
447	34	A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants as Acoustic Models	claim
448	34	A Novel Linear Approach to Camera Calibration from Sphere Images	claim
449	34	Minutiae-based Fingerprint Matching Using Subset Combination	claim
450	34	Pixel-Accurate Representation and Evaluation of Page Segmentation in Document Images	claim
451	34	A Hybrid Approach to Face Detection under Unconstrained Environments	claim
452	34	Rule Extraction from Support Vector Machines: Measuring the Explanation Capability Using the Area under the ROC Curve	claim
453	34	Blind Image Steganalysis Based on Statistical Analysis of Empirical Matrix	claim
454	34	Speaker Verification Using A Novel Set of Dynamic Features	claim
455	34	Affine Invariant Information Embedment for Accurate Camera-Based Character Recognition	claim
456	34	Optimal Cascade Construction for Detection using 3D Models	claim
457	33	Robust Clustering based on Winner-Population Markov Chain	claim
458	33	Semantic Understanding of Continued and Recursive Human Activities	claim
459	33	High Accuracy Handwritten Chinese Character Recognition Using Quadratic Classifiers with Discriminative Feature Extraction	claim
460	33	Activity Recognition from Silhouettes using Linear Systems and Model (In)validation Techniques	claim
461	33	Shape Alignment by Learning a Landmark-PDM Coupled Model	claim
462	33	A Novel Human Gait Recognition Method by Segmenting and Extracting the Region Variance Feature	claim
463	33	An Iterative Algorithm for Segmentation of Isolated Handwritten Words in Gurmukhi Script	claim
464	32	Recognizing Expressions in a New Database Containing Played and Natural Expressions	claim
465	32	Fast Support Vector Machine Classification using linear SVMs	claim
466	32	A two-stage outlier rejection strategy for numerical field extraction in handwritten documents	claim
467	32	Intelligibility of Children with Cleft Lip and Palate: Evaluation by Speech Recognition Techniques	claim
468	32	Multiple Objects Tracking with Multiple Hypotheses Graph Representation	claim
469	32	Dissimilarity-based classification for vectorial representations	claim
470	32	Singular point detection in fingerprints using quadrant change information	claim
471	31	Automatic Adjacency Grammar Generation from User Drawn Sketches	claim
472	31	Scene Identification using Discriminative Patterns	claim
473	31	Line-Based Affine Invariant Object Location Using Transformation Space Decomposition	claim
474	31	Regularized Locality Preserving Learning of Pre-Image Problem in Kernel Principal Component Analysis	claim
475	30	Incremental Vehicle 3-D Modeling from Video	claim
476	30	Simultaneous Gesture Segmentation and Recognition based on Forward Spotting Accumulative HMMs	claim
477	30	Background Robust Object Labeling by Voting of Weight-Aggregated Local Features	claim
478	29	Pose Correction and Subject-Specific Features for Face Authentication	claim
479	29	Bit-pairing Codification for Binary Pattern Projection System	claim
480	29	Gesture Segmentation from a Video Sequence Using Greedy Similarity Measure	claim
481	28	The Role of Featural and Configural Information in Face Classification A Simulation of the Expertise Hypothesis	claim
482	28	Real-Time Detection of Anomalous Objects in Dynamic Scene	claim
483	27	Seeing Around Occluding Objects	claim
484	27	Optimal Global Mosaic Generation from Retinal Images	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers