| Popis: |
This article deals with facial detection and tracking algorithm development. The most efficient method for facial monitoring, namely, template matching technique, was found by considering different tracking techniques. The authors enumerate main drawbacks of the template tracking and improve the algorithm according to the problem set. The following modifications to the template matching method were developed: template averaging, face loss at image edges, scaling the image according to the eye to eye distance, scaling by means of face search, color histogram check and lost face recovery. The article also provides results of functional and stress tests of the tracking algorithm developed. |
