In this paper a criminal detection framework that
could help policemen to recognize the face of a criminal or a
suspect is proposed. The framework is a client-server video based
face recognition surveillance in the real-time. The framework
applies face detection and tracking using Android mobile devices
at the client side and video based face recognition at the server
side. This paper focuses on the development of the client side of
the proposed framework, face detection and tracking using
Android mobile devices. For the face detection stage, robust
Viola-Jones algorithm that is not affected by illuminations is
used. The face tracking stage is based on Optical Flow algorithm.
Optical Flow is implemented in the proposed framework with
two feature extraction methods, Fast Corner Features, and
Regular Features. The proposed face detection and tracking is
implemented using Android studio and OpenCV library, and
tested using Sony Xperia Z2 Android 5.1 Lollipop Smartphone.
Experiments show that face tracking using Optical Flow with
Regular Features achieves a higher level of accuracy and
efficiency than Optical Flow with Fast Corner Features.