ICIP 2005 - PDF Preprint Papers

ICIP 2005 International Conference on Image Processing

3D Immersive Browsing | Click Here

Teaser Browsing | Click Here

Queue Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ICIP-2005 Paper

click to vote

ICIP
2005
IEEE

1625views Image Processing» more ICIP 2005»

Generalized Histogram Intersection Kernel for Image Recognition

15 years 1 months ago

Download perso.lcpc.fr

Histogram Intersection (HI) kernel has been recently introduced for image recognition tasks. The HI kernel is proved to be positive definite and thus can be used in Support Vector ...

Sabri Boughorbel, Jean-Philippe Tarel and Nozha Bo...

posted by jptarel

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	1625	Generalized Histogram Intersection Kernel for Image Recognition
2	417	Nonsubsampled contourlet transform: construction and application in enhancement	claim
3	370	3D face recognition using passive stereo vision	claim
4	350	Atlas-based segmentation of medical images locally constrained by level sets	claim
5	342	Graph cuts segmentation using an elliptical shape prior	claim
6	340	Active contours on statistical manifolds and texture segmentation	claim
7	332	Multi-view face pose classification by tree-structured classifier	claim
8	314	Gray-scale image enhancement using the SMQT	claim
9	296	A generic and automatic content-based approach for improved H.264/MPEG4-AVC video coding	claim
10	284	A bound optimization approach to wavelet-based image deconvolution	claim
11	281	A segmentation method using compound Markov random fields based on a general boundary model	claim
12	269	Shape space sampling distributions and their impact on visual tracking
13	269	Combining interest points and edges for content-based image retrieval	claim
14	267	Visual tracking via efficient kernel discriminant subspace learning	claim
15	255	Image-based stereoscopic stylization	claim
16	250	Nonlinear dimensionality reduction for classification using kernel weighted subspace method	claim
17	248	A fingerprint recognition algorithm using phase-based image matching for low-quality fingerprints	claim
18	246	A probabilistic model for robust face alignment in videos	claim
19	243	Fusion of multiple viewpoint information towards 3D face robust orientation detection	claim
20	241	Interactive partial matching of video sequences in large collections	claim
21	240	Color feature detection and classification by learning	claim
22	237	LIC-based regularization of multi-valued images	claim
23	233	Efficient video mosaicing based on motion analysis	claim
24	233	Pedestrian classification from moving platforms using cyclic motion pattern	claim
25	230	Content-based video copy detection in large databases: a local fingerprints statistical similarity search approach	claim
26	228	A variable background active contour model for automatic detection of thyroid nodules in ultrasound images	claim
27	227	Fast and subpixel precise blob detection and attribution	claim
28	224	Novel likelihood estimation technique based on boosting detector	claim
29	222	The M-term pursuit for image representation and progressive compression	claim
30	222	Coupled geometric and texture PDE-based segmentation	claim
31	222	Approximate separable 3D anisotropic Gauss filter	claim
32	222	Video retrieval using dialogue, keyframe similarity and video objects	claim
33	221	Fine spatial scalability in wavelet based image coding	claim
34	221	No-reference video quality metric based on artifact measurements	claim
35	220	3GPP compliant adaptive wireless video streaming using H.264/AVC	claim
36	218	Dense discontinuous optical flow via contour-based segmentation	claim
37	217	Advances in recursive per-pixel estimation of end-to-end distortion for application in H.264	claim
38	217	Hiding privacy information in video surveillance system	claim
39	214	JPEG 2000 scalar quantization using an optimally frequency localized modulated lapped transform	claim
40	212	A man-machine communication system based on the visual analysis of dynamic gestures	claim
41	212	HMM-based motion recognition system using segmented PCA	claim
42	211	Robust facial expression recognition using local binary patterns	claim
43	211	Curvelet transform on the sphere	claim
44	210	Object representation using colour, shape and structure criteria in a binary partition tree	claim
45	209	Augmented particle filtering for efficient visual tracking	claim
46	209	Adaptive transcoding proxy architecture for video streaming in mobile networks	claim
47	208	Transmission of JPEG2000 code-streams over mobile radio channels	claim
48	207	An active regions approach for the segmentation of 3D biological tissue	claim
49	207	Real time facial expression recognition from image sequences using support vector machines	claim
50	207	Interpolation by asymmetric, two-dimensional cubic convolution	claim
51	205	Comparison of invariant descriptors for object recognition	claim
52	204	Combining MCTF with distributed source coding	claim
53	204	Local manifold matching for face recognition	claim
54	202	Statistical restoration for robust and secure steganography	claim
55	201	H.264/MPEG4-AVC fidelity range extensions: tools, profiles, performance, and application areas	claim
56	200	Curvature-based adaptive remeshing for wavelet-based multiresolution 3D meshes	claim
57	200	Featureless global alignment of multiple images	claim
58	200	On the bandlimitedness of the plenoptic function	claim
59	198	Curve segmentation using directional information, relation to pattern detection	claim
60	198	Higher order polynomials, free form deformations and optical flow estimation	claim
61	197	Color signal decomposition method using 3-D Gamut boundary of multi-primary display	claim
62	197	Localization and security enhancement of block-based image authentication	claim
63	197	Improving particle filter with support vector regression for efficient visual tracking	claim
64	197	Digital "bullet scratches" for images	claim
65	196	New image transforms using hybrid wavelets and directional filter banks: analysis and design	claim
66	196	A nonlinear loop filter for quantization noise removal in hybrid video compression	claim
67	196	Automatic registration of 3D datasets using Gaussian fields	claim
68	195	A motion-based binary partition tree approach to video object segmentation	claim
69	195	Planar homography: accuracy analysis and applications	claim
70	194	Joint source-network error control coding for scalable overlay video streaming	claim
71	194	The impulse responses of block shift-invariant systems and their use for demosaicing algorithms
72	193	Evaluation of disparity map characteristics for stereo image coding	claim
73	193	Minmax strategies for QIM watermarking subject to attacks with memory	claim
74	192	Accuracy estimation of a new omnidirectional 3D vision sensor	claim
75	191	Implicit surface segmentation by minimal paths, applications in 3D medical images	claim
76	191	Using appearance and context for outdoor scene object classification	claim
77	191	View independent face recognition based on kernel principal component analysis of local parts	claim
78	191	3D reconstruction of localized objects from radiographs and based on multiresolution and sparsity	claim
79	190	Multi-step active object tracking with entropy based optimal actions using the sequential Kalman filter	claim
80	189	H.264-compatible spatially scalable video coding with in-band prediction	claim
81	189	Bounding box splitting for robust shape classification	claim
82	189	Wavelet-based illumination normalization for face recognition	claim
83	189	A model free hybrid algorithm for real time tracking	claim
84	188	Robust and fast global motion estimation oriented to video object segmentation	claim
85	188	A frequency-based approach for efficient plenoptic sampling	claim
86	187	New algorithms for fast and accurate AM-FM demodulation of digital images	claim
87	187	An adaptive skin color detection algorithm with confusing backgrounds elimination	claim
88	187	Video coding with MC-EZBC and redundant-wavelet multihypothesis	claim
89	187	Chromatic adaptation and white-balance problem	claim
90	186	Estimating sub-pixel shifts directly from the phase difference	claim
91	186	Artificial neural network-based segmentation and apple grading by machine vision	claim
92	185	Approximation power of directionlets	claim
93	185	Image fusion using a new framework for complex wavelet transforms	claim
94	184	Hybrid recursive energy-based method for robust optical flow on large motion fields	claim
95	184	Mosaic-based 3D scene representation and rendering	claim
96	184	Feedback-based dynamic generalized LDA for face recognition	claim
97	182	An active volumetric model for 3D reconstruction	claim
98	181	A complementary SVMs-based image annotation system	claim
99	181	DCT-domain spatial transcoding using generalized DCT decimation	claim
100	181	Signal estimation using multiple-wavelet representations and Gaussian models	claim
101	180	Video inpainting of occluding and occluded objects	claim
102	180	Color by linear neighborhood embedding	claim
103	179	An adaptive segmentation-based regularization term for image restoration	claim
104	179	An automatic segmentation of color images by using a combination of mixture modelling and adaptive region information: a level s	claim
105	179	A robust and automatic face tracker dedicated to broadcast videos	claim
106	179	Combined error protection and compression using turbo codes for error resilient image transmission	claim
107	178	Semantic discriminant mapping for classification and browsing of remote sensing textures and objects	claim
108	177	Coarse-level object recognition using interlevel products of complex wavelets	claim
109	177	Blind separation of reflections using the image mixtures ratio	claim
110	177	Spatial domain analysis on the focus measurement for light field rendering	claim
111	177	Light field capturing with lensless cameras	claim
112	176	Inverse tensor transfer for novel view synthesis	claim
113	176	Game-theoretic analysis of a semi-fragile watermarking scheme based on SCS	claim
114	175	Spacetime-continuous geometry meshes from multi-view video sequences	claim
115	175	Improved color filter array demosaicking by accurate luminance estimation	claim
116	175	Anisotropic 3D seismic features for robust horizons correlation across faults	claim
117	175	Image matching based on a local invariant descriptor	claim
118	175	Source camera identification based on CFA interpolation	claim
119	174	Bayesian visual tracking with existence process	claim
120	174	Automatic color palette	claim
121	174	A regularization framework for joint blur estimation and super-resolution of video sequences	claim
122	174	Fingerprint indexing based on singular point correlation	claim
123	173	An articulated registration method	claim
124	173	Segmentation and appearance model building from an image sequence	claim
125	173	Lossless image compression using an edge adapted lifting predictor	claim
126	172	Object tracking based on morphological elastic graph matching	claim
127	172	Sharpness measure: towards automatic image enhancement	claim
128	172	Image restoration using a hybrid combination of particle filtering and wavelet denoising	claim
129	172	Nonparametric clustering using quantum mechanics	claim
130	171	Optimal representations in multitree dictionaries with application to compression	claim
131	171	Discrete bandelets with geometric orthogonal filters	claim
132	171	A BPGC-based scalable image entropy coder resilient to errors	claim
133	171	Quality assessment using data hiding on perceptually important areas	claim
134	171	The multiRANSAC algorithm and its application to detect planar homographies	claim
135	170	Asymmetric spread spectrum data-hiding for Laplacian host data	claim
136	170	Color constancy based on the Grey-edge hypothesis	claim
137	170	A modified FCM with optimal Peano scans for image segmentation	claim
138	169	Iterative generation of motion-compensated side information for distributed video coding	claim
139	169	New corner detection algorithm by tangent and vertical axes and case table	claim
140	169	An asymmetric watermarking method for copyright protection utilizing dual bases	claim
141	169	Lossy to lossless image compression using allpass filters	claim
142	169	Automatic classification of breast density	claim
143	169	Network adaptive multiple description coding for JPEG2000	claim
144	168	Face and eye rectification in video conference using affine transform	claim
145	168	Automatic adaptation of streaming multimedia content in a dynamic and distributed environment	claim
146	168	Robust highlight extraction using multi-stream hidden Markov models for baseball video	claim
147	167	Large scale performance measurement of content-based automated image-orientation detection	claim
148	167	Fast trifocal tensor estimation using virtual parallax	claim
149	167	Exploiting discriminant information in elastic graph matching	claim
150	167	Comparative study: face recognition on unspecific persons using linear subspace methods	claim
151	167	Robust face alignment based on local texture classifiers	claim
152	166	Semifragile hierarchical watermarking in a set theoretic framework	claim
153	166	Static human body postures recognition in video sequences using the belief theory	claim
154	166	Joint feature-spatial-measure space: a new approach to highly efficient probabilistic object tracking	claim
155	166	Locally adaptable mathematical morphology	claim
156	165	Locally adaptive multiscale contrast optimization	claim
157	165	Motion vector prediction in multiview video coding	claim
158	165	Bayesian face detection in an image sequence using face probability gradient ascent	claim
159	165	Interleaved S+P pyramidal decomposition with refined prediction model	claim
160	165	Visual tracking using sequential importance sampling with a state partition technique	claim
161	164	Greedy non-linear approximation of the plenoptic function for interactive transmission of 3D scenes	claim
162	164	Eigenwalks: walk detection and biometrics from symmetry patterns	claim
163	164	Complexity-aware live streaming system	claim
164	163	Scene analysis for reducing motion JPEG 2000 video surveillance delivery bandwidth and complexity	claim
165	163	Multi-view image coding with wavelet lifting and in-band disparity compensation	claim
166	163	Scalable multiple description video coding with flexible number of descriptions	claim
167	163	Silhouette-based probabilistic 2D human motion estimation for real-time applications	claim
168	162	Direct image retrieval in JPEG and JPEG2000	claim
169	162	An efficient Rao-Blackwellized particle filter for object tracking	claim
170	162	Tracking objects in video using motion and appearance models	claim
171	162	Camera pose determination from a single view of parallel lines	claim
172	162	A spatio-temporal model of the selective human visual attention	claim
173	161	Processing of textured surfaces represented as surfel sets: representation, compression and geodesic paths	claim
174	161	Detecting spread spectrum watermarks using natural scene statistics	claim
175	160	A spatially adaptive Poissonian image deblurring	claim
176	160	Video compression using structural flow	claim
177	160	Classification and representation of semantic content in broadcast tennis videos	claim
178	159	Influence of the boundary conditions on the result of non-linear image registration	claim
179	159	Multiple image view synthesis for free viewpoint video applications	claim
180	159	Maximum a posteriori image restoration based on a new directional continuous edge image prior	claim
181	159	Detection of semantic objects using description graphs	claim
182	159	Multi-view image coding using 3-D voxel models	claim
183	159	Tracking and segmenting people with occlusions by a sample consensus based method	claim
184	159	Watershed-driven active contours for moving object segmentation	claim
185	159	On object-based compression for a class of dynamic image-based representations	claim
186	159	Spatio-temporal attention model for video content analysis	claim
187	159	Interactive 3D filter design for ultrasound artifact reduction	claim
188	158	A new motion compensation approach for error resilient video coding	claim
189	158	Multiple active contour models based on the EM algorithm	claim
190	158	An adaptive DCT-based Mod-4 steganographic method	claim
191	158	Exponential Radon transform inversion based on harmonic analysis of the Euclidean motion group	claim
192	157	Layered local prediction network with dynamic learning for face super-resolution	claim
193	157	Nonparametric wavelet based texture synthesis	claim
194	157	Aircraft detection and tracking using intelligent cameras	claim
195	157	Extracting micro-structural gabor features for face recognition	claim
196	156	Texture-adaptive mother wavelet selection for texture analysis	claim
197	156	Distributed rate allocation for multi-stream video transmission over ad hoc networks	claim
198	156	Approximations of posterior distributions in blind deconvolution using variational methods	claim
199	156	Evaluation of color spaces for edge classification in outdoor scenes	claim
200	154	Real-time generation of novel views of a dynamic scene using morphing and visual hull	claim
201	154	Noise reduction in 3D images using morphological amoebas	claim
202	154	Segmenting non stationary images with triplet Markov fields	claim
203	154	Learning-based super-resolution of 3D face model	claim
204	154	The tie-zone watershed: definition, algorithm and applications	claim
205	154	Three-dimensional nth derivative of Gaussian separable steerable filters	claim
206	154	Automatic occlusion removal from minimum number of images	claim
207	154	Multi-dimensional infinitely divisible cascades to model the statistics of natural images	claim
208	153	Block-based ordinal co-occurrence matrices for texture similarity evaluation	claim
209	153	Stochastic frame buffers for rate distortion optimized loss resilient video communications	claim
210	153	Bayesian blind source separation for brain imaging	claim
211	152	Progressive bitstream transmission over tandem channels	claim
212	152	Largest-eigenvalue-theory for incremental principal component analysis	claim
213	152	Patch-based BTF synthesis for real-time rendering	claim
214	152	Homogeneity-based directional sigma filtering of video noise	claim
215	152	Consistent image-based measurement and classification of skin color	claim
216	152	Integrating plan-view tracking and color-based person models for multiple people tracking	claim
217	151	Beyond interpolation: optimal reconstruction by quasi-interpolation	claim
218	151	Objective evaluation of the perceptual quality of 3D watermarking	claim
219	150	An efficient algorithm for informed embedding of dirty-paper trellis codes for watermarking	claim
220	150	Complexity/performance trade-offs for robust distributed video coding	claim
221	150	Spatio-temporal texture synthesis and image inpainting for video applications	claim
222	150	SAR images as mixtures of Gaussian mixtures	claim
223	150	Trainable post-processing method to reduce false alarms in the detection of small blotches of archive films	claim
224	150	Expression-invariant face recognition via spherical embedding	claim
225	150	High throughput 2D DCT/IDCT processor for video coding	claim
226	150	An effective human iris code with low complexity	claim
227	149	Learning hidden semantic cues using support vector clustering	claim
228	149	A context adaptation model for the compression of images with a reduced number of colors	claim
229	149	P2CA: a new face recognition scheme combining 2D and 3D information	claim
230	148	Wyner-Ziv video side estimator: conventional motion search methods revisited	claim
231	148	Finding the global minimum for binary image restoration	claim
232	148	Optimal wavelet filter design in scalable video coding	claim
233	148	Analysis of distortion due to packet loss in streaming video transmission over wireless communication links	claim
234	148	Efficient coding of computer generated compound images	claim
235	148	Learning to binarize document images using a decision cascade	claim
236	148	An improved eye feature extraction algorithm based on deformable templates	claim
237	147	Analyzing symmetry in biological systems	claim
238	147	Irregular pattern matching using projections	claim
239	147	Constrained inter-layer prediction for single-loop decoding in spatial scalability	claim
240	147	Correlation estimation for distributed source coding under information exchange constraints	claim
241	147	Adaptive edge enhancement using a neurodynamical model of visual attention	claim
242	147	A tensor-like representation for averaging, filtering and interpolation of 3-D object orientation data	claim
243	146	Two-level adaptive denoising using Gaussian scale mixtures in overcomplete oriented pyramids	claim
244	146	Watermarking JBIG2 text region for image authentication	claim
245	146	Sampling in practice: is the best reconstruction space bandlimited?	claim
246	146	Sampling schemes for 2-D signals with finite rate of innovation using kernels that reproduce polynomials	claim
247	146	A genetic algorithm-based approach to knowledge-assisted video analysis	claim
248	145	Perceptually optimized MPEG compression of synthetic video sequences	claim
249	145	Three-dimensional feature detection using optimal steerable filters	claim
250	145	Measuring the added high frequency energy in compressed video	claim
251	145	Joint demosaicing and denoising	claim
252	145	Gradation approximation for vector based compression of comic images	claim
253	145	Color embedding into gray images	claim
254	145	Low complexity resolution progressive image coding algorithm: progres (progressive resolution decompression)	claim
255	145	Content-based medical image retrieval using dynamically optimized regional features	claim
256	144	Feature selection with nonparametric statistics	claim
257	144	Uncalibrated interpolation of rigid displacements for view synthesis	claim
258	144	Segmenting small regions in the presence of noise	claim
259	144	A multichannel approach to metric-based SAR autofocus	claim
260	144	Universal image coding using multiscale recurrent patterns and prediction	claim
261	144	Performance evaluation of parametric bias field correction	claim
262	144	Hyperspectral imaging: potential in non-destructive analysis of palimpsests	claim
263	144	Using Tsallis entropy into a Bayesian network for CBIR	claim
264	143	Bayesian denoising based on the MAP estimation in wavelet-domain using Bessel K form prior	claim
265	143	High-resolution video streaming in mesh-networked homes	claim
266	142	Low-complexity linear demosaicing using joint spatial-chromatic image statistics	claim
267	142	Lung nodules detection and classification	claim
268	142	Robust tracking with motion estimation and kernel-based color modelling	claim
269	142	Compression by image empirical mode decomposition	claim
270	142	Threshold dynamics for shape reconstruction and disocclusion	claim
271	142	Tracking points on deformable objects with ranklets	claim
272	142	Metrology in uncalibrated images given one vanishing point	claim
273	142	Adaptive resource allocation and frame scheduling for wireless multi-user video streaming	claim
274	141	Real-time segmentation of moving objects in a video sequence by a contrario detection	claim
275	141	Improving frequency domain super-resolution via undersampling model	claim
276	141	Collusion-resistant intentional de-synchronization for digital video fingerprinting	claim
277	141	Saveface and Sirface: appearance-based recognition of faces and facial expressions	claim
278	141	A dynamic Bezier curve model	claim
279	141	Statistical categorization of human histological images	claim
280	141	Fast 2D model-to-image registration using vanishing points for sports video analysis	claim
281	140	Joint source-channel coding of scalable video with partially coded index assignment using Reed-Muller codes	claim
282	140	Multiresolution analysis for meshes with appearance attributes	claim
283	140	Dichromatic-based color constancy using dichromatic slope and dichromatic line space	claim
284	140	A linear prefilter for image sampling with ringing artifact control	claim
285	140	Recognition of human activities using space dependent switched dynamical models	claim
286	140	Two-step variance-adaptive image denoising	claim
287	139	Learning spatially-variable filters for super-resolution of text	claim
288	139	Optimizing of searching co-motion point-pairs for statistical camera calibration	claim
289	139	Unsupervised multiband image segmentation using hidden Markov quadtree and copulas	claim
290	139	Camera calibration with spheres: linear approaches	claim
291	139	Combination of multiple extraction algorithms in the detection of facial features	claim
292	139	A study on view-insensitive gait recognition	claim
293	139	Mining arbitrary-length repeated patterns in television broadcast	claim
294	138	Time-evolving 3D model representation for scalable video coding	claim
295	138	Optimised filters for texture defect detection	claim
296	138	Parameter estimation of multi-dimensional hidden Markov models - a scalable approach	claim
297	137	Dependent bit allocation in multiview video coding	claim
298	137	A palette-based image steganographic method using colour quantisation	claim
299	137	Countering oversegmentation in partitioning-based connectivities	claim
300	137	Human body posture refinement by nonparametric belief propagation	claim
301	136	Combining classifiers for bone fracture detection in X-ray images	claim
302	136	Posture classification in a multi-camera indoor environment	claim
303	136	Predictive compression of dynamic 3D meshes	claim
304	136	Embedded image coding with context partitioning and quantization	claim
305	136	Efficient down-up sampling using DCT kernel for MPEG-21 SVC	claim
306	136	Image-based rendering and tracking of faces	claim
307	136	Frame based multiple description image coding in the wavelet domain	claim
308	136	Viewpoint invariant sign language recognition	claim
309	136	Low complexity streak noise reduction for mobile TV using line selective interpolation of field information	claim
310	135	Tracking multiple cells by correspondence resolution in a sequential Bayesian framework	claim
311	135	Oriented wavelet transform on a quincunx pyramid for image compression	claim
312	134	Multi-part target representation for color tracking	claim
313	134	Vehicle mounted wide FOV stereo for traffic and pedestrian detection	claim
314	134	Efficient neighborhood-based computations on regions using scans	claim
315	134	Reference picture selection in an already MPEG encoded bitstream	claim
316	134	Medical image registration based on random line sampling	claim
317	134	Variational multi-wavelet restoration of noisy images	claim
318	133	Simultaneous super-resolution for video sequences	claim
319	133	Extended direct mode for hierarchical B picture coding	claim
320	133	Dynamic programming algorithm for rate-distortion optimized media streaming	claim
321	133	Fuzzy morphology for omnidirectional images	claim
322	133	Efficient local reflectional symmetries detection	claim
323	132	Video summarization for multiple path communication	claim
324	132	Level set curve evolution partitioning of polarimetric images	claim
325	132	High capacity watermarking using balanced multiwavelet transforms	claim
326	132	Italic detection and rectification	claim
327	132	A transcoding robust data hiding method for image communication applications	claim
328	131	Effective rate control method for minimizing temporal fluctuations in picture quality applicable for MPEG-4 AVC/H.264 encoding	claim
329	131	Image acquisition modeling for super-resolution reconstruction	claim
330	131	Tensor-based factor decomposition for relighting	claim
331	131	Segmentation and tracking of mesoscale eddies in numeric ocean models	claim
332	130	Motion-compensation using variable-size block-matching with binary partition trees	claim
333	130	Semantic kernel learning for interactive image retrieval	claim
334	130	A reconfigurable multi-camera architecture for high resolution objects analysis	claim
335	130	Improved schemes for inter-frame coding in the H.264/AVC standard	claim
336	130	Similarity-based and perception-based image segmentation	claim
337	129	Noise in imaging chains: correlations and predictions	claim
338	129	Non-parametric image super-resolution using multiple images	claim
339	129	Robust and real-time 3D-face model extraction	claim
340	129	Quantifying the coding power of zerotrees of wavelet coefficients: a degree-k zerotree model	claim
341	129	Zoom on target while tracking	claim
342	129	Speckle modeling and reduction in synthetic aperture radar imagery	claim
343	128	Super-resolution from highly undersampled images	claim
344	128	A likelihood function for block-based motion analysis	claim
345	128	Fast distortion-buffer optimized streaming of multimedia	claim
346	128	Error-resilient video transmission using multiple embedded Wyner-Ziv descriptions	claim
347	128	Resistance analysis of scalable video fingerprinting systems under fair collusion attacks	claim
348	128	Custom color enhancements by statistical learning	claim
349	128	Bit allocation and quantizer optimization in multiple description coding with oversampled filterbanks	claim
350	128	System analysis of VLSI architecture for motion-compensated temporal filtering	claim
351	128	Towards arbitrary camera movements for image cube trajectory analysis	claim
352	127	Network embedded FEC (NEF) for video multicast in presence of packet loss correlation	claim
353	127	Fourier transform for the spatial quincunx lattice	claim
354	127	Design goals and solutions for display of hyperspectral images	claim
355	127	Explicit contour model for vehicle tracking with automatic hypothesis validation	claim
356	127	Multigrid computation of rotationally invariant non-linear optical flow	claim
357	127	Multispectral loss-less compression using approximation methods	claim
358	126	Minimization of detail-preserving regularization functional by Newton's method with continuation	claim
359	126	Presegmentation of high-resolution satellite images with a multifractal reconstruction scheme based on an entropy criterium	claim
360	126	Spatiotemporal-chromatic structure of natural scenes	claim
361	126	Flow lookup and biological motion perception	claim
362	126	Towards pose invariant gait reconstruction	claim
363	125	Adaptive de-blocking de-ringing post filter	claim
364	125	Asymmetric multi-phase deformable model for colon segmentation	claim
365	125	Off-line multiple object tracking using candidate selection and the Viterbi algorithm	claim
366	125	An efficient iris recognition algorithm using phase-based image matching	claim
367	124	Face hallucination through dual associative learning	claim
368	124	Using visual features for anti-spam filtering	claim
369	123	The role of the virtual channel in distributed source coding of video	claim
370	123	New higher-order active contour energies for network extraction	claim
371	123	Two-channel predictive multiple description coding	claim
372	123	A hybrid medical image segmentation approach based on dual-front evolution model	claim
373	123	Hexagonal versus orthogonal lattices: a new comparison using approximation theory	claim
374	123	Feature extraction of non-stained melanocyte cells	claim
375	122	Multidimensional phase unwrapping for consistent APF estimation	claim
376	122	Flame detection in video using hidden Markov models	claim
377	122	Shape contexts and Gabor features for face description and authentication	claim
378	122	Range-enhanced active foreground extraction	claim
379	122	Critical encoding rate in combined denoising and compression	claim
380	122	Spiral coding order of macroblocks with applications to SNR-scalable video compression	claim
381	121	Improving performance of interactive categorization of images using relevance feedback	claim
382	121	Symmetric extension for two-channel quincunx filter banks	claim
383	121	Gesture-based video summarization	claim
384	121	The DUDE framework for continuous tone image denoising	claim
385	120	Direct filtering method for image based rendering	claim
386	119	A classification approach for anatomical regions segmentation	claim
387	119	Enhancement of cell boundaries in transmission electron microscopy images	claim
388	119	Generalized optimal thresholding for biometric key generation using face images	claim
389	119	Stable dynamic 3D shape models	claim
390	118	A practical print-scan resilient watermarking scheme	claim
391	118	Rate-distortion optimized video streaming over Internet packet traces	claim
392	118	Image denoising using multiscale directional cosine bases	claim
393	117	Redundant-wavelet watermarking with pixel-wise masking	claim
394	117	An improved pyramid for spatially scalable video coding	claim
395	116	Risk minimization in traitors within traitors in multimedia forensics	claim
396	116	Sequence-level models for distortion-rate behaviour of compressed video	claim
397	115	The virtue of patience when scheduling media in presence of feedback	claim
398	115	Image processing considerations for simple real-time restrictometric fluid-based user interfaces	claim
399	114	Automatic scene comparison and matching in multimodal cytopathological microscopic images	claim
400	114	Natural contrast statistics and the selection of visual fixations	claim
401	112	Generalized Wiener estimation algorithms based on a family of heavy-tail distributions	claim
402	112	Spatially varying gray component replacement for image watermarking	claim
403	112	Fuzzy image segmentation of generic shaped clusters	claim
404	112	An adaptive linear system framework for image distortion analysis	claim
405	111	A weight-adaptive dynamic model for shape segmentation	claim
406	109	Imaging and analysis of angiogenesis for skin transplantation by microangiography	claim
407	108	Multiresolution parametric estimation of transparent motions	claim
408	106	Variable module graphs: a framework for inference and learning in modular vision systems	claim
409	105	Misregistration errors in change detection algorithms and how to avoid them	claim
410	105	Multiple feature models for image matching	claim
411	104	A spatial image hierarchy for compression in image-based-rendering	claim
412	103	Rate allocation algorithms for motion compensated embedded video coders	claim
413	99	Image denoising in nonlinear scale-spaces: automatic scale selection via cross-validation	claim
414	99	Receiver-driven rate-distortion optimized streaming of light fields	claim
415	96	Filter networks for efficient estimation of local 3-D structure	claim
416	95	Unsupervised style classification of document page images	claim
417	95	Warplets: an image-dependent wavelet representation	claim
418	95	Spatiotemporal inpainting for recovering texture maps of partially occluded building facades	claim
419	94	VIPS - a highly tuned image processing software architecture	claim
420	91	Graph cut based segmentation of convoluted objects	claim
421	85	Spatio-temporal video error concealment using priority-ranked region-matching	claim
422	85	Variational segmentation of color images	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers