Face recognition using a similarity-based measure in image database for crime investigation

V. Srisarkun1, J. Cooper1
1Faculty of Informatics, University of Wollongong, NSW, Australia

Tóm tắt

A method to handle searching a face image database (FID) is proposed to support police officers when searching criminal records from a central registration database system (CRDS). The proposed method assumes that each FID consists of a fixable object and object correlation. The proposed method employs a database search, so that all images with a similarity-based measure are retrieved. Consequently, the proposed method is much faster than sequential searching, especially when an additional set of attributes, like scar, is defined. Moreover it requires less storage space.

Từ khóa

#Face recognition #Image databases #Pixel #Image retrieval #Image storage #Information retrieval #Eyebrows #Size measurement #Ear #Informatics

Tài liệu tham khảo

srisarkun, 2001, Traffic Shaping for Frame Relay over ATM Network, Proceeding of the 13th lASTED International conference on Parallel and Distributed Computing and Systems, 469 santini, 1999, Similarity Matching, IEEE Transactions on Pattern Analysis and Machine Intelligence, 4, 34 srisarkun, 2001, Self-Similar Searching in Image Database for Crime Investigation, the twentieth IASTED International Conference on Applied Informatics srisarkun, 2001, A Model for Self-Similar Searching in Face Image Data Processing, the Sixth INFORMS Conference on Information Systems & Technology, 389 srisarkun, 2002, A model for Self-Similar Search in Image Database with Scars, Submitted for publication in The 10th European Conference on Information Systems (ECIS'02) 1998, Learning a Similarity-Based distance measure for Image Database Organization from Human Partitionings of an Image Set, Proc IEEE Workshop on Applications of Computer Vision (WACV 98), 88 10.1109/ICSMC.1997.635154