Francisco Escolano Knihy

Information theory has proved to be effective for solving many computer vision and pattern recognition (CVPR) problems (such as image matching, clustering and segmentation, saliency detection, feature selection, optimal classifier design and many others). Nowadays, researchers are widely bringing information theory elements to the CVPR arena. Among these elements there are measures (entropy, mutual information...), principles (maximum entropy, minimax entropy...) and theories (rate distortion theory, method of types...). This book explores and introduces the latter elements through an incremental complexity approach at the same time where CVPR problems are formulated and the most representative algorithms are presented. Interesting connections between information theory principles when applied to different problems are highlighted, seeking a comprehensive research roadmap. The result is a novel tool both for CVPR and machine learning researchers, and contributes to a cross-fertilization of both areas.

This book covers a range of advanced topics in graph theory and its applications across various domains. It begins with bipartite graph matching techniques for computing graph edit distances and progresses to matching tree structures for medical image registration. The use of graph-based methods for retinal mosaicing and vascular characterization is explored, alongside stereo vision applications for obstacle detection. Key methodologies include graph representation and recognition, partial clique enumeration, and non-subgraph isomorphism bounds. The text delves into correspondence measures for graph matching using discrete quantum walks and quadratic programming approaches to graph edit distance problems. It also discusses image classification through marginalized kernels and compares 3D digital shapes via topological structures. Graph-based segmentation and image processing techniques are presented, including local reasoning in fuzzy attribute graphs and perceptual segmentation of stereo vision 3D images. Additional topics include morphological operators for image filtering, multilevel temporal segmentation of videos, and local influence neighborhoods for edge-preserving image denoising. The book examines graph spectral image smoothing, probabilistic relaxation labeling, and the performance assessment of clustering algorithms. It also addresses qualitative spatial relationships for image interpretation, efficient distance