|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
A person may be automatically identified from an image or video source using a face recognition system. The work of facial recognition is accomplished by extracting facial characteristics from an image of the subject's face. The primary goal of video-based face recognition is to recognize a video face-track of renowned persons using a vast lexicon of fixed face images, while rejecting unfamiliar individuals. Current approaches detect faces by using probability models on a frame-by-frame basis, which is computationally costly when the data set is huge. For face identification and tracking in color images, a weighted Quantum Wolf Optimization is presented in this study. The suggested technique is compared to current approaches, and the test results show that superior categorization efficiency and high confident value are attained owing to little error.
Keyword
Face Recognition, Video Face Tracking, WQWO, frame-by-frame, classification.
PDF Download (click here)
|
|
|
|
|