Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization

ISBN-13: 9781402012334 / Angielski / Twarda / 2003 / 431 str.

F. Mokhtarian;M. Bober

Opis

MPEG-7 is the first international standard which contains a number of key techniques from Computer Vision and Image Processing. The Curvature Scale Space technique was selected as a contour shape descriptor for MPEG-7 after substantial and comprehensive testing, which demonstrated the superior performance of the CSS-based descriptor. Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization is based on key publications on the CSS technique, as well as its multiple applications and generalizations. The goal was to ensure that the reader will have access to the most fundamental results concerning the CSS method in one volume. These results have been categorized into a number of chapters to reflect their focus as well as content. The book also includes a chapter on the development of the CSS technique within MPEG standardization, including details of the MPEG-7 testing and evaluation processes which led to the selection of the CSS shape descriptor for the standard. The book can be used as a supplementary textbook by any university or institution offering courses in computer and information science.

Spis treści

Preface. * 1: Multi-Scale Representations for Free-Form Planar Curves. 1.1. Introduction. 1.2. The Curvature Scale Space Image. 1.3. The Renormalized Curvature Scale Space Image. 1.4. The Resampled Curvature Scale Space Image. 1.5. Evolution and Arc Length Evolution Properties of Planar Curves. 1.6. Experiments, Discussion and Evaluation. 1.7. Concluding Remarks. * 2: Robust Free-Form Object Recognition through Curvature Scale Space. 2.1. Introduction. 2.2. Silhouette-Based Isolated Object Recognition. 2.3. Silhouette-Based Occluded Object Recognition. 2.4. Concluding Remarks. * 3: Image Database Retrieval Based on Shape Content. 3.1. Introduction. 3.2. The CSS Matching Algorithm. 3.3. Global Parameters. 3.4. Performance Evaluation. 3.5. Results for Original Method. 3.6. Comparison to Other methods. 3.7. The Problem of Shallow Concavities. 3.8. Performance Evaluation and Experimental Results. 3.9. Application to Chrysanthemum Leaf Classification. 3.10. Conclusions. * 4: CSS Under Affine Transforms / Non-Rigid Deformations. 4.1. Introduction. 4.2. CSS Image under Affine Transforms. 4.3. Affine Transforms and Affine Databases. 4.4. Affine Length. 4.5. Affine Curvature. 4.6. Implementation Issues. 4.7. Experiments and Results. 4.8. Comparison to Other Methods. 4.9. Concluding Remarks. * 5: Free-Form 3-D Object Retrieval from Arbitrary Viewpoints. 5.1. Introduction. 5.2. Multi-View 3-D Object Representation and Retrieval. 5.3. Robust Automatic Selection of Optimal Views. 5.4. Free-Form 3-D Object Retrieval with Occlusion from Arbitrary Viewpoints. 5.5. Conclusions. * 6: MPEG-7 Standardisation of the CSS Shape Descriptor. 6.1. Introduction. 6.2. MPEG-7 Overview. 6.3. MPEG-7 Shape Descriptors. 6.4. Contour-Based Shape Descriptor. 6.5. Region-Based Shape Descriptor. 6.6. MPEG-7 Performance Testing Methodology and Test Sets. 6.7. Experimental Performance Analysis and MPEG-7 Selection Process. 6.8. Example Applications of the CSS Shape Descriptor. 6.9. Conclusions. * 7: Robust Image Corner Detection through Curvature Scale Space. 7.1. Introduction. 7.2. literature Survey. 7.3. Canny Edge Detector. 7.4. Original CSS Corner Detection Method. 7.5. Original CSS Experimental Results and Discussion. 7.6. Enhanced CSS Corner Detection Method. 7.7. New CSS Experimental Results and Discussion. 7.8. Performance Evaluation of Corner Detection Algorithms under Similarity and Affine Transforms. 7.9. Conclusions. * 8: Fast Active Contour Convergence through CSS Filtering. 8.1. Introduction. 8.2. Literature Survey. 8.3. Smoothed Active Contour (SAC). 8.4. Experimental Results. 8.5. Conclusions. * 9: Multi-Scale Contour Data Compression and Reconstruction Using CSS. 9.1. Introduction. 9.2. Spline Fitting Techniques. 9.3. Contour Data Reconstruction throug

O autorze

Farzin Mokhtarian is a Senior Lecturer at the Centre for Vision, Speech, and Signal Processing at the University of Surrey, Guildford, UK. He received his degrees from the Johns Hopkins University, Baltimore, MD, and the University of British Columbia, Vancouver, Canada. He worked for Schlumberger-Doll Research Lab, Ridgefield, CT, and NTT Basic Research Labs, Tokyo. He is well known for his research in the areas of 2-D and 3-D shape representation and analysis. Miroslaw Bober is Principal Scientist at the Visual Information Laboratory of Mitsubishi Electric ITE B.V., Guildford, UK. He received his M.Sc. in electrical engineering from University of Mining and Metallurgy, Cracow, Poland and then M.Sc. and Ph.D. degrees from the University of Surrey, UK. He has been chairing the work of the MPEG-7 Standard, Visual part. His scientific interests include motion analysis, video coding, multimedia signal processing, and pattern recognition.