Face Detection and Gesture Recognition for Human-Computer Interaction / Edition 1

by Ming-Hsuan Yang, Narendra Ahuja

Overview

Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyzing image sequences, or video understanding. Video understanding deals with understanding of video sequences, e. g. , recognition of gestures, activities, facial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvious overlap with computer vision. The main goal of computer graphics is to gener­ ate and animate realistic looking images, and videos. Researchers in computer graphics are increasingly employing techniques from computer vision to gen­ erate the synthetic imagery. A good example of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is de­ rived from real images using computer vision techniques. Here the shift is from synthesis to analysis followed by synthesis.

Product Details

ISBN-13:	9780792374091
Publisher:	Springer US
Publication date:	08/31/2001
Series:	The International Series in Video Computing , #1
Edition description:	2001
Pages:	182
Product dimensions:	6.40(w) x 9.30(h) x 0.90(d)

Table of Contents

1. Introduction.- 1. Face Detection.- 2. Gesture Recognition.- 3. Book Overview.- 2. Detecting Faces in Still Images.- 1. Introduction.- 2. Detecting Faces In A Single Image.- 3. Face Image Databases and Performance Evaluation.- 4. Discussion and Conclusion.- 3. Recognizing Hand Gestures Using Motion Trajectories.- 1. Introduction.- 2. Motivation and Approach.- 3. Motion Segmentation.- 4. Skin Color Model.- 5. Geometric Analysis.- 6. Motion Trajectories.- 7. Recognizing Motion Patterns Using Time-Delay Neural Network.- 8. Experiments.- 9. Discussion and Conclusion.- 4. Skin Color Model.- 1. Proposed Mixture Model.- 2. Statistical Tests.- 3. Experimental Results.- 4. Applications.- 5. Discussion and Conclusion.- 5. Face Detection Using Multimodal Density Models.- 1. Introduction.- 2. Previous Work.- 3. Mixture of Factor Analyzers.- 4. Mixture of Linear Spaces Using Fisher’s Linear Discriminant.- 5. Experiments.- 6. Discussion and Conclusion.- 6. Learning to Detect Faces with SNoW.- 1. Introduction.- 2. Previous Work.- 3. SNoW Learning Architecture.- 4. Learning to Detect Faces.- 5. Empirical Results.- 6. Analyzing SNoW: Theoretical and Empirical Results.- 7. Generation and Efficiency.- 8. Discussion and Conclusion.- 7. Conclusion and Future Work.- 1. Conclusion.- 2. Future Work.- Appendices.- A– Covariance of Two Normally Distributed Variables.- B– Conditional Distributions of Multiple Correlation Coefficient.- References.

Editorial Reviews

Researchers have been working under the premise that a computer can recognize information about a user's identity, state, and intent from facial expression and hand motions. Because of the immense number of variables in processing facial images (scale, location, orientations, pose, etc) the first step is getting computers to recognize faces. Gesture recognition is similarly complicated. Yang (Honda R&D Americas, Inc.) and Ahuja (computer science, U. of Illinois at Urbana-Champaign) present their own work in these related fields and summarize some recent findings by other researchers. They present an algorithm for extracting and recognizing motion patterns, present experimental results on motion patterns related to 40 American Sign Language gestures, discuss a model that extracts skin tone regions for the reduction of computation needed, present experimental results for the model, and describe a (Sparse Network of Winnows) SnoW-based face detector. Finally future directions of research are examined. Annotation c. Book News, Inc., Portland, OR (booknews.com)