Mathematical Methodologies in Pattern Recognition and Machine Learning

This volume features key contributions from the International Conference on Pattern Recognition Applications and Methods, (ICPRAM 2012,) held in Vilamoura, Algarve, Portugal from February 6th-8th, 2012. The conference provided a major point of collaboration between researchers, engineers and practitioners in the areas of Pattern Recognition, both from theoretical and applied perspectives, with a focus on mathematical methodologies. Contributions describe applications of pattern recognition techniques to real-world problems, interdisciplinary research, and experimental and theoretical studies which yield new insights that provide key advances in the field.  This book will be suitable for scientists and researchers in optimization, numerical methods, computer science, statistics and for differential geometers and mathematical physicists.

InhaltsangabeOn order equivalences between distance and similarity measures on sequences and trees.- Scalable Corpus Annotation by Graph Construction and Label Propagation.- Computing the reeb graph for triangle meshes with active contours.- Efficient Computation of Voronoi Neighbors based on Polytope search in Pattern Recognition.- Estimation of the common oscillation for Phase Locked Matrix Factorization.- ASSET: Approximate Stochastic Subgradient Estimation Training for Support Vector Machines.- Pitch-sensitive Components emerge from Hierarchical Sparse Coding of Natural Sounds.- Generative Embeddings based on Rican Mixtures: Application to KernelBased Discriminative Classification of Magnetic Resonance Images.-Single-Frame Signal Recovery Using a Similarity-Prior Based on Pearson Type VII MRF.- Tracking solutions of time varying linear inverse problems.- Stacked Conditional Random Fields Exploiting Structural Consistencies.- Segmentation of Vessel Geometries from Medical Images using GPF Deformable Model.- Robust Deformable Model for Segmenting the Left Ventricle in 3D volumes of Ultrasound Data.- Algorithm to maintain linear element in 3D Level Set Topology Optimization.- Facial Expression recognition using Log-Euclidean statistical shape models.