Self-Similar Searching in Image Database for Crime Investigation

V. Srisarkun and J. Cooper (Australia)

Keywords

photograph image database, selfsimilar searching, simulation, correlation and object relation.

Abstract

The Department of Local Administration is one of the most important departments of the Ministry of Interior in Thailand. One of the main objectives of the department is to provide one-stop and immediate electronic civil registration service and issuing citizen ID Card at the local registrar offices. To build a database and computer system for civil registration and ID Card, which can later be utilized by other government agencies all over the country in order to increase efficiency in the internal administration. For example, the Royal Police Department and the Crime Combat Section can also share the database from the central registration system implemented by the Department of Local Administration. Frequently, individual registration database and photographs are needed for the crime investigation when trying to locate that person, tracking his/her history or identify their images. According to the updated information, there are 30,918,051 male and 31,398,931 female citizens all together. In this paper a method to handle searching for photographs image database (PID) is proposed to support police officers when searching criminal records. The proposed method assumes that each photograph image consists of a fixable object and object correlation. A database search is employed by using the proposed method, so that all images with self-similar will be retrieved. As a result the proposed method is much faster than sequential searching and requires less space.

Important Links:



Go Back