Dissertation/Thesis Abstract

Extracting Key Features for Analysis and Recognition in Computer Vision
by Gao, Hui, Ph.D., The Ohio State University, 2006, 164; 10835745
Abstract (Summary)

In Computer Vision applications, there often exist the need to extract features to facilitate the process of analysis and recognition. In our key feature approach, we first study a computational framework of modeling human action styles, which extracts key motion trajectories for analysis and recognition assuming a given representation (e.g., trajectories and three-mode PCA). By emphasizing those key trajectories, the framework is capable of improving the modeling efficiency and accuracy, while being adaptive to multiple action style modeling criteria. We then extend the key feature approach in considering a general problem of recognition and analysis without an explicit representation (e.g., using raw images). We want to automatically extract key features to form an optimal internal representation of the data (images), which is a fundamental problem in Computer Vision research. By emphasizing the key information for representation, our approach is capable of improving the efficiency and accuracy for analysis and recognition in a wide range of applications in Computer Vision.

Indexing (document details)
Advisor: Davis, James
Commitee:
School: The Ohio State University
Department: Computer and Information Science
School Location: United States -- Ohio
Source: DAI-B 79/09(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Computer science
Keywords: Biological motion, Dimensionality reduction, Feature extraction, Linear discriminant analysis, Modeling human action styles, Three-mode pca
Publication Number: 10835745
ISBN: 9780355967265
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest