Many vision problems have to deal with di?erent entities (regions, lines, line junctions, etc.) and their relationships. These entities together with their re- tionships may be encoded using graphs or hypergraphs. The structural inf- mation encoded by graphs allows computer vision algorithms to address both the features of the di?erent entities and the structural or topological relati- ships between them. Moreover, turning a computer vision problem into a graph problem allows one to access the full arsenal of graph algorithms developed in computer science. The Technical Committee (TC15, http://www.iapr.org/tcs.html) of the IAPR (International Association for Pattern Recognition) has been funded in order to federate and to encourage research work in these ?elds. Among its - tivities, TC15 encourages the organization of special graph sessions at many computer vision conferences and organizes the biennial workshop GbR. While being designed within a speci?c framework, the graph algorithms developed for computer vision and pattern recognition tasks often share constraints and goals with those developed in other research ?elds such as data mining, robotics and discrete geometry. The TC15 community is thus not closed in its research ?elds but on the contrary is open to interchanges with other groups/communities.
Author(s): Alain Bretto, Luc Gillibert (auth.), Luc Brun, Mario Vento (eds.)
Series: Lecture Notes in Computer Science 3434 : Image Processing, Computer Vision, Pattern Recognition, and Graphics
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2005
Language: English
Pages: 384
Tags: Pattern Recognition; Image Processing and Computer Vision; Computer Graphics; Discrete Mathematics in Computer Science; Data Structures
Front Matter....Pages -
Hypergraph-Based Image Representation....Pages 1-11
Vectorized Image Segmentation via Trixel Agglomeration....Pages 12-22
Graph Transformation in Document Image Analysis: Approaches and Challenges....Pages 23-34
Graphical Knowledge Management in Graphics Recognition Systems....Pages 35-44
A Vascular Network Growth Estimation Algorithm Using Random Graphs....Pages 45-53
A Linear Generative Model for Graph Structure....Pages 54-62
Graph Seriation Using Semi-definite Programming....Pages 63-71
Comparing String Representations and Distances in a Natural Images Classification Task....Pages 72-81
Reduction Strings: A Representation of Symbolic Hierarchical Graphs Suitable for Learning....Pages 82-91
Representing and Segmenting 2D Images by Means of Planar Maps with Discrete Embeddings: From Model to Applications....Pages 92-121
Inside and Outside Within Combinatorial Pyramids....Pages 122-131
The GeoMap : A Unified Representation for Topology and Geometry....Pages 132-141
Pyramids of n-Dimensional Generalized Maps....Pages 142-152
Towards Unitary Representations for Graph Matching....Pages 153-161
A Direct Algorithm to Find a Largest Common Connected Induced Subgraph of Two Graphs....Pages 162-171
Reactive Tabu Search for Measuring Graph Similarity....Pages 172-182
Tree Matching Applied to Vascular System....Pages 183-192
A Graph-Based, Multi-resolution Algorithm for Tracking Objects in Presence of Occlusions....Pages 193-202
Coarse-to-Fine Object Recognition Using Shock Graphs....Pages 203-212
Adaptive Pyramid and Semantic Graph: Knowledge Driven Segmentation....Pages 213-222
A Graph-Based Concept for Spatiotemporal Information in Cognitive Vision....Pages 223-232
Approximating the Problem, not the Solution: An Alternative View of Point Set Matching....Pages 233-242
Defining Consistency to Detect Change Using Inexact Graph Matching....Pages 243-252
Asymmetric Inexact Matching of Spatially-Attributed Graphs....Pages 253-262
From Exact to Approximate Maximum Common Subgraph....Pages 263-272
Automatic Learning of Structural Models of Cartographic Objects....Pages 273-280
An Experimental Comparison of Fingerprint Classification Methods Using Graphs....Pages 281-290
Collaboration Between Statistical and Structural Approaches for Old Handwritten Characters Recognition....Pages 291-300
Decision Trees for Error-Tolerant Graph Database Filtering....Pages 301-311
Recovery of Missing Information in Graph Sequences....Pages 312-321
Tree-Based Tracking of Temporal Image....Pages 322-331
Protein Classification with Kernelized Softassign....Pages 332-341
Local Entropic Graphs for Globally-Consistent Graph Matching....Pages 342-351
Edit Distance Based Kernel Functions for Attributed Graph Matching....Pages 352-361
A Robust Graph Partition Method from the Path-Weighted Adjacency Matrix....Pages 362-372
Recent Results on Heat Kernel Embedding of Graphs....Pages 373-382
Back Matter....Pages -
