Sebe / Lew Robust Computer Vision

Theory and Applications
2003
ISBN: 978-94-017-0295-9
Verlag: Springer Netherland
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 26, 215 Seiten, eBook

Reihe: Computational Imaging and Vision

"During the past decade, researchers in computer vision have found that probabilistic machine learning methods are extremely powerful. This book describes some of these methods. In addition to the Maximum Likelihood framework, Bayesian Networks, and Hidden Markov models are also used. Three aspects are stressed: features, similarity metric, and models. Many interesting and important new results, based on research by the authors and their collaborators, are presented.

Although this book contains many new results, it is written in a style that suits both experts and novices in computer vision."

Zielgruppe

Research

Autoren/Hrsg.

Sebe, N.

Lew, M.S.

Inhaltsverzeichnis

Foreword. Preface.

1: Introduction. 1. Visual Similarity. 2. Evaluation of Computer Vision Algorithms. 3. Overview of the Book.

2: Maximum Likelihood Framework. 1. Introduction. 2. Statistical Distributions. 3. Robust Statistics. 4. Maximum Likelihood Estimators. 5. Maximum Likelihood in Relation to Other Approaches. 6. Our Maximum Likelihood Approach. 7. Experimental Setup. 8. Concluding Remarks.

3: Color Based Retrieval. 1. Introduction. 2. Colorimetry. 3. Color Models. 4. Color Based Retrieval. 5. Experiments with the Corel Database. 6. Experiments with the Objects Database. 7. Concluding Remarks.

4: Robust Texture Analysis. 1. Introduction. 2. Human Perception of Texture. 3. Texture Features. 4. Texture Classification Experiments. 5. Texture Retrieval Experiments. 6. Concluding Remarks.

5: Shape Based Retrieval. 1. Introduction. 2. Human Perception of Visual Form. 3. Active Contours. 4. Invariant Movements. 5. Experiments. 6. Conclusions.

6: Robust Stereo Matching and Motion Tracking. 1. Introduction. 2. Stereo Matching. 3. Stereo Matching Algorithms. 4. Stereo Matching Experiments. 5. Motion Tracking Experiments. 6. Concluding Remarks.

7: Facial Expression Recognition. 1. Introduction. 2. Emotion Recognition. 3. Face Tracking and Feature Extraction.4. The Static Approach: Bayesian Network Classifiers. 5. The Dynamic Approach: Expression Recognition Using Multi-level HMM. 6. Experiments. 7. Summary and Discussion.

References. Index.

Über Autor(innen)

received his PhD degree from Leiden University in 2001. Currently, he is an Assistant Professor at Leiden University in the Netherlands. His main interest is in the fields of computer vision and pattern recognition, in particular content-based retrieval and robust techniques in computer vision. He was co-editing the proceedings of the International Conference on Image and Video Retrieval 2002. He is also acting as the technical program co-chair for the International Conference on Image and Video Retrieval 2003.

received his PhD degree in Electrical Engineering from the University of Illinois at Urbana-Champaign. He is currently an Associate Professor at Leiden University in the Netherlands. He has published over 100 scientific papers and helped organize several large conferences including IEEE Multimedia, ACM Multimedia, and the International Conference on Image and Video Retrieval.