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

Abstrak

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