Abstract

Methods of least square matching and face detection based on the template were studied. In order to explore a new method for face detection in color images, an algorithm using least square and face template was presented. Firstly, color face templates are compounded by using human face images. Then the least square matching method is implemented to operate each detecting image and the color face template. Finally, the principle of threshold decision is utilized in the algorithm to determine human face or non-face. There are three kinds of templates, which include frontal, right, and left face templates are utilized to test the algorithm. Experimental verifications are carried out to evaluate performance in RGB, YCrCb and HSI color space. Results demonstrate that a reliable face right judgment rete achieved in the experimental images, and YCrCb color space has the best effect. Correct determination rates of front, left, and right face are 97.7%, 96.8%, and 97.6%.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.