Energy Minimization Methods in Computer Vision and Pattern Recognition: 6th International Conference, EMMCVPR 2007, Ezhou, China, August 27-29, 2007, ProceedingsAlan L. Yuille This volume contains the papers presented at the Sixth International Conference on Energy Minimization Methods on Computer Vision and Pattern Recognition (EMMCVPR 2007), held at the Lotus Hill Institute, Ezhou, Hubei, China, August 27–29, 2007. The motivation for this conference is the realization that many problems in computer vision and pattern recognition can be formulated in terms of probabilistic inference or optimization of energy functions. EMMCVPR 2007 addressed the critical issues of representation, learning, and inference. Important new themes include pr- abilistic grammars, image parsing, and the use of datasets with ground-truth to act as benchmarks for evaluating algorithms and as a way to train learning algorithms. Other themes include the development of efficient inference algorithms using advanced techniques from statistics, computer science, and applied mathematics. We received 140 submissions for this workshop. Each paper was reviewed by three committee members. Based on these reviews we selected 22 papers for oral presen- tion and 15 papers for poster presentation. This book makes no distinction between oral and poster papers. We have organized these papers in seven sections on al- rithms, applications, image parsing, image processing, motion, shape, and thr- dimensional processing. Finally, we thank those people who helped make this workshop happen. We - knowledge the Program Committee for their help in reviewing the papers. |
Contents
An Effective Multilevel Algorithm Based on Simulated Annealing for Bisecting Graph | 1 |
Szemer ́edis Regularity Lemma and Its Applications to Pairwise Clustering and Segmentation | 13 |
Exact Solution of Permuted Submodular MinSum Problems | 28 |
Efficient Shape Matching Via Graph Cuts | 39 |
Simulating Classic Mosaics with Graph Cuts | 55 |
An Energy Minimisation Approach to Attributed Graph Regularisation | 71 |
A Pupil Localization Algorithm Based on Adaptive Gabor Filtering and Negative Radial Symmetry | 87 |
Decomposing Document Images by Heuristic Search | 97 |
An a Contrario Approach for Parameters Estimation of a MotionBlurred Image | 267 |
Improved Object Tracking Using an AdaptiveColour Model | 280 |
Vehicle Tracking Based on Image Alignment in Aerial Videos | 295 |
Probabilistic Fiber Tracking Using Particle Filtering and Von MisesFisher Sampling | 303 |
Compositional Object Recognition Segmentation and Tracking in Video | 318 |
Bayesian OrderAdaptive Clustering for Video Segmentation | 334 |
Dynamic Feature Cascade for Multiple Object Tracking with Trackability Analysis | 350 |
Discrete Skeleton Evolution | 362 |
Corrected InverseDenoising Filter for Image Restoration | 112 |
Skew Detection Algorithm for Form Document Based on Elongate Feature | 127 |
Active Appearance Models Fitting with Occlusion | 137 |
Combining Left and Right Irises for Personal Authentication | 145 |
BottomUp Recognition and Parsing of the Human Body | 153 |
Methodology Annotation Tool and Benchmarks | 169 |
An Automatic Portrait System Based on AndOr Graph Representation | 184 |
Object Category Recognition Using Generative Template Boosting | 198 |
Bayesian Inference for Layer Representation with Mixed Markov Random Field | 213 |
Dichromatic Reflection Separation from a Single Image | 225 |
Noise Removal and Restoration Using VotingBased Analysis and Image Segmentation Based on Statistical Models | 242 |
A Boosting Discriminative Model for Moving Cast Shadow Detection | 253 |
Shape Classification Based on Skeleton Path Similarity | 375 |
Removing ShapePreserving Transformations in SquareRoot Elastic SRE Framework for Shape Analysis of Curves | 387 |
Shape Analysis of Open Curves in real3 with Applications | 399 |
EnergyBased Reconstruction of 3D Curves for Quality Control | 414 |
3D Computation of Gray Level Cooccurrence in Hyperspectral Image Cubes | 429 |
Continuous Global Optimization in Multiview 3D Reconstruction | 441 |
A New Bayesian Method for Range Image Segmentation | 453 |
Marked Point Process for Vascular Tree Extraction on Angiogram | 467 |
Surface Reconstruction from LiDAR Data with Extended Snake Theory | 479 |
493 | |
Other editions - View all
Common terms and phrases
algorithm Analysis and Machine And-Or graph approach Bayesian blur boundary candidate classification clustering color compositions Computer Vision constraints contour control points corresponding curves database dataset defined denote detection diffuse distance distribution edge EMMCVPR energy error estimation extracted fiber filter form documents frame framework function Gabor filter Gaussian geodesic given gradient graph cut histogram IEEE IEEE Trans IEEE Transactions image segmentation input image iteration labeling layer LiDAR LNCS Machine Intelligence Markov Markov random field minimization MinSum mosaic node noise NURBS object obtained occlusion optical flow optimal original image parameter parsing parsing graph partition path Pattern Analysis Pattern Recognition pixels problem proposed method pruning reconstruction region representation sample shadow shown skeleton sketch space specular statistical step structure submodular subset surface surface reconstruction templates tensor texture threshold tile tracking vector vector sigma vertices voxel zone