Developing Viola Jones' algorithm for detecting and tracking a human face in video file

Abstract

Face detecting and tracking in video clips is very important in many areas of
daily life. All institutions, public departments, streets, and large stores use
cameras from a security point of view, and detecting and tracking human
faces is necessary for indexing and preserving information concerning the
visual media. This paper presents a novel method for hybridizing the
Viola_Jones face detection algorithm to track and identify a human face in
video sequences. The method represents a combination of Viola Jones'
algorithm with a measured normalized cross-correlation (NCC) algorithm
with a template matching method using the Manhattan distance measure
equation in the video between successive sequences After that, the fuzzy
logic method is added in comparing the image of the face to be detected with
the images of templates taken in the proposed algorithm, which increased the
accuracy of the results, which reached 99.3%.