Face recognition technology for law enforcement applications
Rama Chellappa, Saad A. Sirohey · 1994
The goal of this report is to relate existing face recognition technology to law enforcement applications.These applications range from static matching of controlled photographs as in mugshot matching to surveillance video images and have different constraints in terms of complexity of processing requirements and thus present a wide range of different technical challenges.Over the last 20 years researchers in psychophysics, neural sciences and engineering, image processing, analysis and computer vision have investigated a number of issues related to face recognition by humans and machines.The ongoing research activities have been given a renewed emphasis over the last five years.The existing techniques and systems have been tested on different sets of images of varying complexities.Also, very little synergism exists between studies in psychophysics and the engineering literature.Most importantly, there exist no evaluation or benchmarking studies using large databases with the image quality that arises in law enforcement applications.In this report, we first present different possible scenarios that arise in law enforcement applications.Special constraints that are present in these applications are pointed out.This is followed by a brief overview of the literature on face recognition in the psychophysics community.We then present a detailed overview of more than twenty years of research done in the engineering community.Techniques for segmentation/location of the face, feature extraction and recognition are reviewed.Global transform and feature based methods using statistical, structural and neural classifiers are summarized.A brief summary of recognition using face profiles and range image data is also given.Examples of face recognition and matching techniques applied to specific law T enforcement problems are pointed out.Real-time recognition from video images acquired in a cluttered scene such as an airport is probably the most challenging problem of face recognition.As not much has been reported on this problem, we discuss several existing technologies in the image understanding literature that could potentially impact this problem.Given the numerous theories and techniques that are applicable to face recognition, it is clear that evaluation and benchmarking of these algorithms is crucial.We discuss several issues such as data collection, performance metrics and evaluation of systems and techniques that are relevant to law enforcement.Finally, a summary and conclusions are given.