Image Retrieval from a Forensic Cartridge Case Database - Multimedia Database Retrieval: Technology and Applications - page 144

Chapter 6
Image Retrieval from a Forensic Cartridge
Case Database

Abstract This chapter presents a content-based image retrieval method for firearm
identification. The reference and the corresponding cartridge base case images
are aligned according to the phase-correlation criterion on the transform domain.
The informative segments of the breech face marks are identified by a cross-
covariance coefficient in a window located locally in the image space. Mea-
surements of edge density for these segments are made to compute effective
correlation areas for image matching. This image matching system can attain
significant improvement in image-correlation results, compared with traditional
image-matching methods for firearm identification. The system will enable forensic
science to compile a large-scale image database to perform a correlation of cartridge
case bases, in order to identify firearms that involve pairwise alignments and
comparisons.

6.1 Introduction

The comparison of ballistic images taken from ballistic evidence found at a crime
scene against reference images is the main issue in forensic science for firearm
identification. The development of accurate analytical tools and systems is highly
desirable. This chapter presents a method to address this issue based on two
techniques: automatic registration of images containing breech face marks, and
content-based matching of cartridge base case images.
Recently, there has been much research interest in techniques dealing with image
processing and the statistical methods used to ascertain ballistic specimens [ 166 ].
By employing such techniques, a ballistic information system (BIS) can provide
the automated association of ballistic samples—correlation lists against a given
query specimen. In view of the difficulty in obtaining a complete match, this system
can only provide a statistically viable match or an investigative lead that allows
a forensic examiner to microscopically examine the evidence, to then arrive at an
identification that can be used to apprehend and convict a criminal.
An effective correlator is therefore the most important module in the BIS. It
interprets the contents of ballistic images in a collection, and ranks these images
according to the degree of relevance to the user query. This chapter presents a