ICPR 2004 - PDF Preprint Papers

ICPR 2004 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-2004 Paper

click to vote

ICPR
2004
IEEE

485views computer vision» more ICPR 2004»

Sketched Symbol Recognition using Zernike Moments

2 years 3 months ago

Download embedded.eecs.berkeley.edu

A. Richard Newton, Heloise Hwawen Hse

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	485	Sketched Symbol Recognition using Zernike Moments	claim
2	227	Building Detection by Dempster-Shafer Fusion of LIDAR Data and Multispectral Aerial Imagery	claim
3	213	Fast Tone Mapping for High Dynamic Range Images	claim
4	197	Boosting Nested Cascade Detector for Multi-View Face Detection	claim
5	107	3D Face Pose Tracking From an Uncalibrated Monocular Camera	claim
6	105	Developing Assistant Tools for Geometric Camera Calibration: Assessing the Quality of Input Images	claim
7	104	Multi Feature Path Modeling for Video Surveillance	claim
8	101	Three-Dimensional Model Based Face Recognition	claim
9	101	A Hybrid Face Recognition Method using Markov Random Fields	claim
10	100	A Strongly Coupled Architecture for Contextual Object and Scene Identification	claim
11	99	Pruning Local Feature Correspondences Using Shape Context	claim
12	97	Vignetting Distortion Correction Method for High Quality Digital Imaging	claim
13	95	Face Recognition Based on Discriminative Manifold Learning	claim
14	94	Historical Document Image Enhancement Using Background Light Intensity Normalization	claim
15	94	An FPGA-Based Architecture for Real Time Image Feature Extraction	claim
16	93	Integration of Feature Distributions for Colour Texture Segmentation	claim
17	92	Kernel-Based Method for Tracking Objects with Rotation and Translation	claim
18	90	Multi-View Face Detection under Complex Scene based on Combined SVMs	claim
19	88	Multiscale Fourier Descriptor for Shape-Based Image Retrieval	claim
20	87	Evaluation of Model-Based Interactive Flower Recognition	claim
21	87	Recognizing Human Actions: A Local SVM Approach	claim
22	87	Parallelizing Motion Segmentation by Perceptual Organization of XYT	claim
23	81	Improved Adaptive Gaussian Mixture Model for Background Subtraction	claim
24	80	Facial Image Retrieval Based on Demographic Classification	claim
25	79	Object Detection using Background Context	claim
26	79	Fusion of Vision, 3D Gyro and GPS for Camera Dynamic Registration	claim
27	77	Car Detection Based on Multi-Cues Integration	claim
28	76	Improvement of Bidirectional Recurrent Neural Network for Learning Long-Term Dependencies	claim
29	76	Auto-Calibration of Multi-Projector Display Walls	claim
30	71	Robust Feature Matching Across Widely Separated Color Images	claim
31	70	Wide Baseline Matching Through Homographic Transformation	claim
32	70	An Efficient Method to Detect Facial Fiducial Points for Face Recognition	claim
33	70	A Vision-Based Vehicle Identification System	claim
34	69	Outlier Detection Using k-Nearest Neighbour Graph	claim
35	69	Multiresolution Spatial Partitioning for Shape Representation	claim
36	68	Filtering with Gray-Code Kernels
37	67	Estimating the Stretching Characteristics of Fiber Bundles in Microscopic Images	claim
38	66	A New Color Image Segmentation Algorithm based on Watershed Transformation	claim
39	66	Object Classification with Multi-Scale Autoconvolution	claim
40	66	High Frequency Component Compensation based Super-Resolution Algorithm for Face Video Enhancement	claim
41	65	Illumination and Expression Invariant Face Recognition with One Sample Image	claim
42	65	Vision Based Fire Detection	claim
43	64	Italic Font Recognition Using Stroke Pattern Analysis on Wavelet Decomposed Word Images	claim
44	64	Large Scale Feature Selection Using Modified Random Mutation Hill Climbing	claim
45	64	A Variational Approach for Color Image Segmentation	claim
46	64	3D Shape-based Face Recognition using Automatically Registered Facial Surfaces	claim
47	63	Human Action Segmentation via Controlled Use of Missing Data in HMMs	claim
48	63	Morphological Analysis of Spatio-Temporal Patterns for the Segmentation of Cyclic Human Activities	claim
49	62	Velocity Adaptation of Space-Time Interest Points	claim
50	62	Inter-Stage Feature Propagation in Cascade Building with AdaBoost	claim
51	62	Detection of Artificial Structures in Natural-Scene Images Using Dynamic Trees	claim
52	62	3D Model Reconstruction by Constrained Bundle Adjustment	claim
53	61	Extending Dynamic Range of Two Color Images under Different Exposures	claim
54	61	Estimation of 3D Shape of Warped Document Surface for Image Restoration	claim
55	61	Speech Driven Facial Animation using a Hidden Markov Coarticulation Model	claim
56	61	An Algorithm for Real Time Eye Detection in Face Images	claim
57	59	Principal Component Analysis for Online Handwritten Character Recognition	claim
58	59	Support Vector Machine with Local Summation Kernel for Robust Face Recognition	claim
59	58	Complex Human Activity Recognition for Monitoring Wide Outdoor Environments	claim
60	58	Evaluation of Three Optical Flow-Based Observation Models for Tracking	claim
61	58	Affine Propagation for Surface Reconstruction in Wide Baseline Stereo	claim
62	58	Shape Retrieval using Concavity Trees	claim
63	57	3D Free-Form Object Recognition in Range Images Using Local Surface Patches	claim
64	57	Shape Metamorphism using p-Laplacian Equation	claim
65	57	An Undecimated Wavelet Transform Based Denoising, PPCA Based Pulse Modeling and Detection-Classification of PD Signals	claim
66	56	Edge Detection in Range Images of Piled Box-like Objects	claim
67	55	Towards Shape from Shading under Realistic Photographic Conditions	claim
68	55	Motion Capture Based on Color Error Maps in a Distributed Collaborative Environment	claim
69	55	Shape Reconstruction and Image Restoration for Non-Flat Surfaces of Documents with a Stereo Vision System	claim
70	54	Visual Learning and Recognition of a Probabilistic Spatio-Temporal Model of Cyclic Human Locomotion	claim
71	54	Feature Subset Selection using ICA for Classifying Emphysema in HRCT Images	claim
72	54	Tooth Contour Extraction for Matching Dental Radiographs	claim
73	54	Competitive Coding Scheme for Palmprint Verification	claim
74	54	To FRAME or not to FRAME in Probabilistic Texture Modelling?	claim
75	54	Morphology Analysis of Physiological Signals Using Hidden Markov Models	claim
76	54	Integration of Range Images in a Multi-View Stereo System	claim
77	53	Action and Simultaneous Multiple-Person Identification Using Cubic Higher-Order Local Auto-Correlation	claim
78	53	Probabilistic Object Tracking Using Multiple Features	claim
79	53	Adaptive Clustering Ensembles	claim
80	53	Moving Object Extraction with a Localized Pyramid	claim
81	53	Simple Calibration Without Metric Information Using an Isoceles Trapezoid	claim
82	52	Learned Probabilistic Image Motion Models for Event Detection in Videos	claim
83	52	Local Fisher Embedding	claim
84	52	Probabilistic People Tracking for Occlusion Handling	claim
85	52	Object Recognition Using Segmentation for Feature Detection	claim
86	52	Image and Feature Co-Clustering	claim
87	52	Fast Object and Pose Recognition Through Minimum Entropy Coding	claim
88	52	Object-Based Video Coding Using Pixel State Analysis	claim
89	51	Reconstructing a Dynamic Surface from Video Sequences Using Graph Cuts in 4D Space-Time	claim
90	51	Entropy-Based Measures for Clustering and SOM Topology Preservation Applied to Content-Based Image Indexing and Retrieval	claim
91	51	Bayesian Face Recognition Based on Gaussian Mixture Models	claim
92	51	Object-Based and Event-Based Semantic Video Adaptation	claim
93	51	Robust Real-Time Detection, Tracking, and Pose Estimation of Faces in Video Streams	claim
94	50	Elastic Face, An Anatomy-Based Biometrics Beyond Visible Cue	claim
95	50	Discrimination of Machine-Printed from Handwritten Text Using Simple Structural Characteristics	claim
96	50	Did the great masters use optical projections while painting? Perspective Comparison of Paintings and Photographs of Renaissance	claim
97	50	Reflectance Estimation from Motion under Complex Illumination	claim
98	50	Articulate Hand Motion Capturing Based on a Monte Carlo Nelder-Mead Simplex Tracker	claim
99	50	Face Tracking in Meeting Room Scenarios Using Omnidirectional Views	claim
100	50	Dense Wide-Baseline Disparities from Conventional Stereo for Immersive Videoconferencing	claim
101	50	Novel Seed Selection for Multiple Objects Detection and Tracking	claim
102	49	Grey Scale Image Skeletonisation from Noise-Damped Vector Potential	claim
103	49	A Generic Camera Calibration Method for Fish-Eye Lenses	claim
104	49	Image Segmentation Through Energy Minimization Based Subspace Fusion	claim
105	49	Data Dependent Classifier Fusion for Construction of Stable Effective Algorithms	claim
106	49	Online Appearance-Based Face and Facial Feature Tracking	claim
107	49	CVML - An XML-based Computer Vision Markup Language	claim
108	49	Image Retrieval with Relevance Feedback Based on Graph-Theoretic Region Correspondence Estimation	claim
109	49	Using Multiple Graphics Cards as a General Purpose Parallel Computer : Applications to Computer Vision	claim
110	49	Nearest Intra-Class Space Classifier for Face Recognition	claim
111	49	An Image Watermarking Scheme using HVS Characteristics and Spread Transform	claim
112	49	Optimizing Nearest Neighbour in Random Subspaces using a Multi-Objective Genetic Algorithm	claim
113	49	BTF Image Space Utmost Compression and Modelling Method	claim
114	49	Embedding Motion in Model-Based Stochastic Tracking	claim
115	49	Extraction and Clustering of Motion Trajectories in Video	claim
116	48	Robust Phase Correlation	claim
117	48	ART Extension for Description, Indexing and Retrieval of 3D Objects	claim
118	48	Vector Field Smoothing Via Heat Flow	claim
119	48	Multiblock-Fusion Scheme for Face Recognition	claim
120	48	Skin Detection: A Bayesian Network Approach	claim
121	48	Reconstruction of Medical Images by Perspective Shape-from-Shading	claim
122	48	Color Calibration for a Dermatological Video Camera System	claim
123	48	Extracting a Gaze Region with the History of View Directions	claim
124	48	Relevant Linear Feature Extraction Using Side-information and Unlabeled Data	claim
125	47	Non Stationary Bayesian Image Restoration	claim
126	47	Linear Discriminant Analysis and Discriminative Log-linear Modeling	claim
127	47	Rejection Strategies for Offline Handwritten Sentence Recognition	claim
128	47	Enhancements for Local Feature Based Image Classification	claim
129	47	Estimation of the Size and Location of Multiple Area Light Sources	claim
130	47	Training of Classifiers Using Virtual Samples Only	claim
131	47	Maximizing Validity in 2D Motion Analysis	claim
132	47	Attribute Relevance in Multiclass Data Sets Using the Naive Bayes Rule	claim
133	47	A Novel Energy Minimization Criterion for Color Image Segmentation	claim
134	47	Robust Modelling of Local Image Structures and Its Application to Medical Imagery	claim
135	47	Integration Frameworks for Large Scale Cognitive Vision Systems - An Evaluative Study	claim
136	47	High Accuracy Classification of EEG Signal	claim
137	47	Recognition of Airborne Fungi Spores in Digital Microscopic Images	claim
138	46	Real-time Estimation of Light Source Environment for Photorealistic Augmented Reality	claim
139	46	Prioritized Region of Interest Coding in JPEG2000	claim
140	46	Using Adapted Levenshtein Distance for On-Line Signature Authentication	claim
141	46	Off-line Handwriting Identification Using HMM Based Recognizers	claim
142	46	Thermal Face Recognition Over Time	claim
143	46	Hand Gesture Recognition: Self-Organising Maps as a Graphical User Interface for the Partitioning of Large Training Data Sets	claim
144	46	Compact Representation of Multidimensional Data Using Tensor Rank-One Decomposition	claim
145	46	A Probabilistic Approach to Learning Costs for Graph Edit Distance	claim
146	46	Alignment of Multiple Non-Overlapping Axially Symmetric 3D Datasets	claim
147	46	Biometrics: A Grand Challenge	claim
148	46	Image Segmentation by Shape Particle Filtering	claim
149	46	Fast Robust GA-Based Ellipse Detection	claim
150	45	The Multistage Approach to Information Extraction in Degraded Document Images	claim
151	45	Modification of Watershed Transformation for Images, Containing Small Objects	claim
152	45	OntoDoc: An Ontology-Based Query System for Digital Libraries	claim
153	45	Direct Condensing: An Efficient Voronoi Condensing Algorithm for Nearest Neighbor Classifiers	claim
154	45	Unsupervised Image Segmentation Using A Simple MRF Model with A New Implementation Scheme	claim
155	45	Tracking Periodic Motion using Bayesian Estimation	claim
156	45	An Immersive Telepresence System with a Locomotion Interface Using High-Resolution Omnidirectional Movies	claim
157	45	Estimating Surface Shape and Extending Known Structure using Specular Reflections	claim
158	45	Simplest Representation Yet for Gait Recognition: Averaged Silhouette	claim
159	45	Active Mass Estimation With Haptic Vision	claim
160	45	Rapid Spline-based Kernel Density Estimation for Bayesian Networks	claim
161	45	Face Recognition Based on the Appearance of Local Regions	claim
162	45	Filter Algorithm for 3D Pose Estimation of Maneuvering Target	claim
163	45	3D Surface Reconstruction by Self-Consistent Fusion of Shading and Shadow Features	claim
164	45	Estimation of the Bayesian Network Architecture for Object Tracking in Video Sequences	claim
165	45	Photometric Stereo Under Blurred Observations	claim
166	44	Model-Free Augmented Reality by Virtual Visual Servoing	claim
167	44	Real-Time Face Detection Using Boosting in Hierarchical Feature Spaces	claim
168	44	Finding Region Correspondences for Wide Baseline Stereo	claim
169	44	Coordinate Systems Reconstruction for Graphical Documents by Hough-feature Clustering and Geometric Analysis	claim
170	44	Linear and Non-linear Geometric Object Matching with Implicit Representation	claim
171	44	Rehashing for Bayesian Geometric Hashing	claim
172	44	Learning Sample Subspace with Application to Face Detection	claim
173	44	Graph Method for Generating Affine Moment Invariants	claim
174	44	Rotation Estimation from Spherical Images	claim
175	44	Structural Representation of Speech for Phonetic Classification	claim
176	44	Face Authentication Test on the BANCA Database	claim
177	44	The Morphological Top-Hat Operator Generalised to Multi-Channel Images	claim
178	44	Probabilistic Classification Between Foreground Objects and Background	claim
179	44	Face Verification System Architecture Using Smart Cards	claim
180	44	Image Analysis Through Local Information Measures	claim
181	44	An Enhanced Appearance Model for Ultrasound Image Segmentation	claim
182	44	Generating Omnifocus Images Using Graph Cuts and a New Focus Measure	claim
183	43	Convexity Recognition Using Multi-Scale Autoconvolution	claim
184	43	Surface Tortuosity and its Application to Analyzing Cracks in Concrete	claim
185	43	Kernel Autoassociator with Applications to Visual Classification	claim
186	43	Robust Carving for Non-Lambertian Objects	claim
187	43	Iterative Figure-Ground Discrimination	claim
188	43	Estimation of Arbitrary Camera Motion in MPEG Videos	claim
189	43	Active Learning to Recognize Multiple Types of Plankton	claim
190	43	Online Learning of Color Transformation for Interactive Object Recognition under Various Lighting Conditions	claim
191	43	Selecting Models from Videos for Appearance-Based Face Recognition	claim
192	43	Feature Selection and Gene Clustering from Gene Expression Data	claim
193	43	3D Scanning Using Spatiotemporal Orientation	claim
194	43	Landscape of Clustering Algorithms	claim
195	43	Activity Summarisation and Fall Detection in a Supportive Home Environment	claim
196	43	Pose Clustering Guided by Short Interpretation Trees	claim
197	43	Graph Based Image Matching	claim
198	43	Multi-Class Extensions of the GLDB Feature Extraction Algorithm for Spectral Data	claim
199	43	A New Optimised De Bruijn Coding Strategy for Structured Light Patterns	claim
200	43	Automatic Morphological Detection of Otolith Nucleus	claim
201	43	FPGA based Real-Time Visual Servoing	claim
202	42	Tangent Vector Kernels for Invariant Image Classification with SVMs	claim
203	42	Discriminative Distance Measures for Image Matching	claim
204	42	Parameterisation Invariant Statistical Shape Models	claim
205	42	On-Line Adaptive Background Modelling for Audio Surveillance	claim
206	42	Global Localization and Relative Pose Estimation Based on Scale-Invariant Features	claim
207	42	Multi-level Anchorperson Detection Using Multimodal Association	claim
208	42	Tracking Soccer Players using the Graph Representation	claim
209	42	ICA-FX Features for Classification of Singing Voice and Instrumental Sound	claim
210	42	Prescient Paper: Multimedia Document Creation with Document Image Matching	claim
211	42	Laser Stripe Peak Detector for 3D Scanners. A FIR Filter Approach	claim
212	42	Combining Sensory and Symbolic Data for Manipulative Gesture Recognition	claim
213	42	Missing Microarray Data Estimation Based on Projection onto Convex Sets Method	claim
214	42	Estimation of Distance to Planar Surfaces and Type of Material with Infrared Sensors	claim
215	42	Rigid Motion Estimation from Non-Central Catadioptric Images	claim
216	42	Sequence Recognition with Scanning N-Tuple Ensembles	claim
217	42	Prototype Setting for Elastic Matching-Based Image Pattern Recognition	claim
218	42	Pose Invariant Affect Analysis using Thin-Plate Splines	claim
219	42	Supervised Nonparametric Information Theoretic Classification	claim
220	42	Robust Local Max-Min Filters by Normalized Power-Weighted Filtering	claim
221	42	Seamless Video Editing	claim
222	42	Improving MMI with Enhanced-FCM for the Fusion of Brain MR and SPECT Images	claim
223	42	Visual Pattern Recognition in the Years Ahead	claim
224	41	Type-2 Fuzzy Hidden Markov Models to Phoneme Recognition	claim
225	41	Super-Resolving Compressed Video with Large Artifacts	claim
226	41	Spectral Sound Gap Filling	claim
227	41	Automated Detection of Solar Loops by the Oriented Connectivity Method	claim
228	41	Unsupervised Band Selection for Multispectral Images using Information Theory	claim
229	41	A Consistency-Based Model Selection for One-Class Classification	claim
230	41	Discriminatory Power of Handwritten Words for Writer Recognition	claim
231	41	An Efficient Three-Stage Classifier for Handwritten Digit Recognition	claim
232	41	On Classifier Domains of Competence	claim
233	41	Classification Probability Analysis of Principal Component Null Space Analysis	claim
234	41	Corner Detection Using Support Vector Machines	claim
235	41	Gaussian Noise Elimination in Colour Images by Vector-Connected Filters	claim
236	41	Exploring Human Eye Behaviour using a Model of Visual Attention	claim
237	41	Parallel Tracking of All Soccer Players by Integrating Detected Positions in Multiple View Images	claim
238	41	Object Categorization via Local Kernels	claim
239	41	Systematic Static Shadow Detection	claim
240	41	Efficient Model Selection for Kernel Logistic Regression	claim
241	40	Selective Sampling Based on the Variation in Label Assignments	claim
242	40	Detecting Deformable Objects with Flexible Shape Priors	claim
243	40	Applying A Hybrid Method To Handwritten Character Recognition	claim
244	40	Conformal Method for Quantitative Shape Extraction: Performance Evaluation	claim
245	40	Physics-Based Extraction of Intrinsic Images from a Single Image	claim
246	40	Semantic Object Segmentation by a Spatio-Temporal MRF Model	claim
247	40	Nearest Neighbor Ensemble	claim
248	40	Signal Discrimination Using a Support Vector Machine for Genetic Syndrome Diagnosis	claim
249	40	An Energy Minimisation Approach to Stereo-Temporal Dense Reconstruction	claim
250	40	Serialized Unsupervised Classifier for Adaptative Color Image Segmentation: Application to Digitized Ancient Manuscripts	claim
251	40	Invariants to Convolution with Circularly Symmetric PSF	claim
252	40	Hierarchical Object Indexing and Sequential Learning	claim
253	40	Rigorous Accuracy Bounds for Calibrated Stereo Reconstruction	claim
254	40	Recognition of Unconstrained Legal Amounts Handwritten on Chinese Bank Checks	claim
255	40	A SOFM Improves a Real Time Quality Assurance Machine Vision System	claim
256	40	Gaussian Energy Functions for Registration without Correspondences	claim
257	40	Shooting the Lecture Scene Using Computer-controlled Cameras Based on Situation Understanding and Evaluation of Video Images	claim
258	40	Large Scene Reconstruction with Local Details Recovery	claim
259	40	Efficient Calculation of the Complete Optimal Classification Set	claim
260	40	Bernoulli Mixture Models for Binary Images	claim
261	39	Media Content and Type Selection from Always-on Wearable Video	claim
262	39	Human Perception Based Color Image Quantization	claim
263	39	Recognition of Expression Variant Faces Using Weighted Subspaces	claim
264	39	Probabilistic Combination of Multiple Modalities to Detect Interest	claim
265	39	Object Class Recognition using Images of Abstract Regions	claim
266	39	A Symmetric Convexity Measure	claim
267	39	Efficient Coding of Stroke-Rendered Paintings	claim
268	39	Structural Graph Matching With Polynomial Bounds On Memory and on Worst-Case Effort	claim
269	39	Detecting Human Motion with Support Vector Machines	claim
270	39	Single Camera Stereo using Planar Parallel Plate	claim
271	39	Deformable Geometry Model Matching by Topological and Geometric Signatures	claim
272	39	A Bayesian Approach for 3D Models Retrieval Based on Characteristic Views	claim
273	39	Two-Stage Classification System combining Model-Based and Discriminative Approaches	claim
274	39	A Pattern Synthesis Technique with an Efficient Nearest Neighbor Classifier for Binary Pattern Recognition	claim
275	39	Eye Tracking Using Markov Models	claim
276	39	Incorporating Prior Knowledge into SVM for Image Retrieval	claim
277	39	Event Semantics in Two-person Interactions	claim
278	38	Face Pose Estimation and its Application in Video Shot Selection	claim
279	38	Online Multicamera Tracking with a Switching State-Space Model	claim
280	38	Motion Analysis Using Frame Differences with Spatial Gradient Measures	claim
281	38	Decoder Banks: Versatility, Automation, and High Accuracy without Supervised Training	claim
282	38	Building and Registering Parameterized 3D Models of Vessel Trees for Visualization during Intervention	claim
283	38	A Fast Discriminant Approach to Active Object Recognition and Pose Estimation	claim
284	38	Perceptual Grouping for Contour Extraction	claim
285	38	High Quality Isosurface Generation from Volumetric Data and Its Application to Visualization of Medical CT data	claim
286	38	An Efficient Automatic Redeye Detection and Correction Algorithm	claim
287	38	Evaluation of Tracking Reliability Metrics based on Information Theory and Normalized Correlation	claim
288	38	Spin Images for Retrieval of 3D Objects by Local and Global Similarity	claim
289	38	Ontology and Taxonomy Collaborated Framework for Meeting Classification	claim
290	38	A Trainable Low-level Feature Detector	claim
291	38	Neural Network-Based Proper Names Extraction in Fax Images	claim
292	38	Multi-Resolution Template Kernels	claim
293	38	A Software Algorithm Prototype for Optical Recognition of Embossed Braille	claim
294	37	A Unification Framework for Tree and Block Wavelet Encoders	claim
295	37	Resampling for Face Detection by Self-Adaptive Genetic Algorithm	claim
296	37	Probabilistic Tracking with Adaptive Feature Selection	claim
297	37	Model Based Object Recognition by Robust Information Fusion	claim
298	37	Non-Iterative Approach to Multiple 2D Motion Estimation	claim
299	37	Perceptual Distance Normalization for Appearance Detection	claim
300	37	Segmentation and Classification of Meeting Events using Multiple Classifier Fusion and Dynamic Programming	claim
301	37	Relaxation Labeling Processes for Protein Secondary Structure Prediction	claim
302	37	Learning Classes for Video Interpretation with a Robust Parallel Clustering Method	claim
303	37	Object Recognition Using Composed Receptive Field Histograms of Higher Dimensionality	claim
304	37	Automated Visual Identification of Characters in Situation Comedies	claim
305	37	Synchronization and Calibration of Camera Networks from Silhouettes	claim
306	37	Dense Estimation of Surface Reflectance Properties Based on Inverse Global Illumination Rendering	claim
307	37	Background Removal System for Object Movies	claim
308	37	A Unified Information-Theoretic Approach to the Correspondence Problem in Image Registration	claim
309	37	Image Retrieval by Local Evaluation of Nonlinear Kernel Functions around Salient Points	claim
310	37	Learning Spatial Context from Tracking using Penalised Likelihoods	claim
311	37	Regression Analysis and Automorphic Orbits in Free Groups of Rank 2	claim
312	37	Resolution Enhancement by AdaBoost	claim
313	37	Localization of Saliency through Iterative Voting	claim
314	37	A Two-Stage Approach for Segmentation and Recognition of Handwritten Digit Strings Collected from Mail Pieces	claim
315	36	On Performance Evaluation of Face Detection and Localization Algorithms	claim
316	36	A Fast Recursive 3D Model Reconstruction Algorithm for Multimedia Applications	claim
317	36	Joint Spatial and Temporal Structure Learning for Task based Control	claim
318	36	A Deformable Model Driven Method for Handling Clothes	claim
319	36	Texture Analysis using Level-crossing Statistics	claim
320	36	Robust KLT Tracking with Gaussian and Laplacian of Gaussian Weighting Functions	claim
321	36	A Probabilistic Framework for Joint Head Tracking and Pose Estimation	claim
322	36	Connected Rotation-Invariant Size-Shape Granulometries	claim
323	36	From Massively Parallel Image Processors to Fault-Tolerant Nanocomputers	claim
324	36	A Statistical Shape Model without Using Landmarks	claim
325	36	Morphological Tagging Approach in Document Analysis of Invoices	claim
326	36	Vision-Based Traffic Measurement System	claim
327	36	Statistical Classification of Raw Textile Defects	claim
328	36	Neural Network Based Modeling and Color Rendering for Mixed Reality	claim
329	35	Selecting Canonical Views for View-Based 3-D Object Recognition	claim
330	35	Classification Error Rate for Quantitative Evaluation of Content-based Image Retrieval Systems	claim
331	35	An Iris Image Synthesis Method Based on PCA and Super-Resolution	claim
332	35	Analysis of Rotational Robustness of Hand Detection with a Viola-Jones Detector	claim
333	35	Face Detection Using Discriminating Feature Analysis and Support Vector Machine in Video	claim
334	35	Towards Surface Regularization via Medial Axis Transitions	claim
335	35	Detecting Abnormal Regions in Colonoscopic Images by Patch-based Classifier Ensemble	claim
336	35	Galilean-Diagonalized Spatio-Temporal Interest Operators	claim
337	35	Robust Image Denoising Using Kernel-Induced Measures	claim
338	35	Optimal Inference for Hierarchical Skeleton Abstraction	claim
339	35	On the use of Anthropometry in the Invariant Analysis of Human Actions	claim
340	35	Off-line Handwritten Textline Recognition Using a Mixture of Natural and Synthetic Training Data	claim
341	35	Non-Isotropic Regularization of the Correspondence Space in Stereo-Vision	claim
342	35	Principal Flow for Tubular Objects with Non-Circular Cross-Sections	claim
343	35	Switching Particle Filters for Efficient Real-time Visual Tracking	claim
344	35	Sample Size Estimation using the Receiver Operating Characteristic Curve	claim
345	34	The Characterization of Classification Problems by Classifier Disagreements	claim
346	34	Learning High-level Independent Components of Images through a Spectral Representation	claim
347	34	Combining Null Space-based Gabor Features for Face Recognition	claim
348	34	Hierarchical Probabilistic Models for Video Object Segmentation and Tracking	claim
349	34	Spontaneous Handwriting Recognition and Classification	claim
350	34	Levels of Detail Control Based on Correlation Analysis Between Surface Position and Direction	claim
351	34	Adjustable Invariant Features by Partial Haar-Integration	claim
352	34	A Hierarchical Projection Pursuit Clustering Algorithm	claim
353	34	An Efficient Technique for Protein Sequence Clustering and Classification	claim
354	34	Surface Sculpting with Stochastic Deformable 3D Surfaces	claim
355	34	Precise Estimation of High-Dimensional Distribution and Its Application to Face Recognition	claim
356	34	Talking Faces - Technologies and Applications	claim
357	34	An Integrated Decoding Framework for Audio Watermark Extraction	claim
358	33	Information Fusion in Face Identification	claim
359	33	Multiple-Exemplar Discriminant Analysis for Face Recognition	claim
360	33	Transitions of the Pre-Symmetry Set	claim
361	33	Robust Detection of People in Thermal Imagery	claim
362	33	Pattern Matching by Sequential Subdivision of Transformation Space	claim
363	33	Location and Recognition of Flashlight Projections for Visual Interfaces	claim
364	33	A System Identification Approach for Video-based Face Recognition	claim
365	32	A Rival Penalized EM Algorithm towards Maximizing Weighted Likelihood for Density Mixture Clustering with Automatic Model Selection	claim
366	32	Optimally Regularised Kernel Fisher Discriminant Analysis	claim
367	32	Improving Cut Detection in MPEG Videos by GOP-Oriented Frame Difference Normalization	claim
368	32	A Graph-Based Approach to Corner Matching Using Mutual Information as a Local Similarity Measure	claim
369	32	Gesture Tracking and Recognition for Lecture Video Editing	claim
370	32	Robust Playfield Segmentation using MAP Adaptation	claim
371	31	Local Context in Non-Linear Deformation Models for Handwritten Character Recognition	claim
372	31	A New Approach For The Registration of Images With Inconsistent Differences	claim
373	31	Text Detection from Natural Scene Images: Towards a System for Visually Impaired Persons	claim
374	31	Jet Based Feature Classification	claim
375	31	A Wrapper-Based Approach to Image Segmentation and Classification	claim
376	31	Condensation Tracking through a Hough Space	claim
377	30	An Embedded Real-time Vision System for 24-hour Indoor/Outdoor Car-Counting Applications	claim
378	30	Incorporating Temporal Context with Content for Classifying Image Collections	claim
379	29	Stealth Vision for Protecting Privacy	claim
380	29	Non-linear Reflectance Model for Bidirectional Texture Function Synthesis	claim
381	29	Periodic Nonlinear Principal Component Neural Networks for Humanoid Motion Segmentation, Generalization, and Generation	claim
382	29	A System to Detect Houses and Residential Street Networks in Multispectral Satellite Images	claim
383	29	Group-based Relevance Feedback with Support Vector Machine Ensembles	claim
384	28	Registration of an Uncalibrated Image Pair to a 3D Surface Model	claim
385	27	Dining Activity Analysis Using a Hidden Markov Model	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers