A new algorithm for human face detection using skin color tone
Human face recognition systems have gained a considerable attention during last decade due to its vast applications in the field of computer and advantages over previous biometric methods. There are many applications with respect to security, sensitivity and secrecy. Face detection is the most impor...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOSR Journal
2013
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/36709/ http://irep.iium.edu.my/36709/ http://irep.iium.edu.my/36709/1/JCE-13.pdf |
| Summary: | Human face recognition systems have gained a considerable attention during last decade due to its vast applications in the field of computer and advantages over previous biometric methods. There are many applications with respect to security, sensitivity and secrecy. Face detection is the most important and first step of recognition system. This paper introduces a new approach to face detection systems using the skin color of a subject. This system can detect a face regardless of the background of the picture, which is an important phase for face identification. The images used in this system are color images which give additional information about the images than the gray images provide. In face detection, the two respective classes are the "face area" and the "non-face area". This new approach to face detection is based on color tone values specially defined for skin area detection within the image frame. This system first resizes the image, and then separates it into its component R, G, and B bands. These bands are transformed into another color space which is YCbCr space and then into YC’bC’r space (the skin color tone). The morphological process is implemented on the presented image to make it more accurate. At last, the projection face area is taken by this system to determine the face area. Experimental results show that the proposed algorithm is good enough to localize a human face in an image with an accuracy of 92.69%. |
|---|