Accession Number : ADA322283

Title :   Name-It: Association of Face and Name in Video.

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE

Personal Author(s) : Satoh, Shin ichi ; Kanade, Takeo

PDF Url : ADA322283

Report Date : 20 DEC 1996

Pagination or Media Count : 19

Abstract : This paper proposes a novel approach to extract meaningful content information from video by collaborative integration of image understanding and natural language processing. As an actual example, we developed a system that associates faces and names in videos, called Name-It, which is given news videos as a knowledge source, then automatically extracts face and name association as content information. The system can infer the name of a given unknown face image, or guess faces which are likely to have the name given to the system. This paper explains the method with several successful matching results which reveal effectiveness in integrating heterogeneous techniques as well as the importance of real content information extraction from video, especially face-name association.

Descriptors :   *IMAGE PROCESSING, *INFORMATION RETRIEVAL, *VIDEO INTEGRATION, DATA BASES, ALGORITHMS, SOFTWARE ENGINEERING, NEURAL NETS, EIGENVECTORS, OPTICAL COMMUNICATIONS, OPTICAL IMAGES, ASSOCIATIVE PROCESSING, PATTERN RECOGNITION, MAN COMPUTER INTERFACE, VIDEO SIGNALS, OPTICAL STORAGE, NATURAL LANGUAGE, IMAGE REGISTRATION, FACE(ANATOMY).

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE