Computational Intelligence in Multi-Feature Visual Pattern Recognition

Beschreibung

This book presents a collection of computational intelligence algorithms that addresses issues in visual pattern recognition such as high computational complexity, abundance of pattern features, sensitivity to size and shape variations and poor performance against complex backgrounds. The book has 3 parts. Part 1 describes various research issues in the field with a survey of the related literature. Part 2 presents computational intelligence based algorithms for feature selection and classification. The algorithms are discriminative and fast. The main application area considered is hand posture recognition. The book also discusses utility of these algorithms in other visual as well as non-visual pattern recognition tasks including face recognition, general object recognition and cancer / tumor classification. Part 3 presents biologically inspired algorithms for feature extraction. The visual cortex model based features discussed have invariance with respect to appearance and size of the hand, and provide good inter class discrimination. A Bayesian model of visual attention is described which is effective in handling complex background problem in hand posture recognition. The book provides qualitative and quantitative performance comparisons for the algorithms outlined, with other standard methods in machine learning and computer vision. The book is self-contained with several figures, charts, tables and equations helping the reader to understand the material presented without instruction.
This book presents a collection of computational intelligence algorithms that addresses issues in visual pattern recognition such as high computational complexity, abundance of pattern features, sensitivity to size and shape variations and poor performance against complex backgrounds. The book has 3 parts. Part 1 describes various research issues in the field with a survey of the related literature. Part 2 presents computational intelligence based algorithms for feature selection and classification. The algorithms are discriminative and fast. The main application area considered is hand posture recognition. The book also discusses utility of these algorithms in other visual as well as non-visual pattern recognition tasks including face recognition, general object recognition and cancer / tumor classification. Part 3 presents biologically inspired algorithms for feature extraction. The visual cortex model based features discussed have invariance with respect to appearance and size of the hand, and provide good inter class discrimination. A Bayesian model of visual attention is described which is effective in handling complex background problem in hand posture recognition.The book provides qualitative and quantitative performance comparisons for the algorithms outlined, with other standard methods in machine learning and computer vision. The book is self-contained with several figures, charts, tables and equations helping the reader to understand the material presented without instruction.
Comprehensive coverage of various steps issues in visual pattern recognition for young researchers and students Contains focused discussion on hand gesture recognition for experienced researchers and scientists Includes algorithms that could be extended to other pattern recognition tasks like face and object recognition The block diagrams and pseudo codes provided help better understanding of the algorithms presented The tables with performance comparisons help the reader to make the right choice of the algorithm for a certain application Includes supplementary material: sn.pub/extras

Autor*in

Pramod Kumar Pisharady

Themen in »Computational Intelligence in Multi-Feature Visual Pattern Recognition«

Artificial Intelligence Face Recognition Feature Extraction Algorithms Fuzzy-Rough Approach Gesture Recognition Hand Posture Recognition Machine Learning Visual Pattern Recognition

Stimmen zu »Computational Intelligence in Multi-Feature Visual Pattern Recognition«

Details

Link teilen