Abstract

Face detection is one of the important problem of image processing and pattern recognition. Most of the existing algorithm takes the frame of fixed size in order to detect the faces in any image. In any image it is possible that the image that are near are larger in size in comparison to the faces that are in back side. In this paper we proposed a novel approach for detection of faces of variable size frame. To detect the location of face we used template based algorithm for detecting the circle of eyes. In proposed algorithm we used upright, frontal faces, for a single gray scale images with decent resolution and under good lighting condition. The experiment were performed in windows operating system with matlab2010a software.

References

• Krestinin, I.A., Seredin, O.S.: Excluding cascading classifier for face detection. Proc. of the 19th Int. Conf. on Computer Graphics and Vision, 380–381 (2009).
• Kienzle, W., Bakir, G., Franz, M., Scholkopf, B.: Face detection – efficient and rank deficient, Advan. in neural inform. process. systems 17, 2005. – P. 673–680 (2005).
• Nikolay Degtyarev and Oleg Seredin, Tula State University. Comparitive testing of face detection algorithm The original publication is available at www.springerlink.com.
• Jesorsky, O., Kirchberg, K.J., Frischholz, R.W.: Robust face detection using the hausdorff distance, Lecture Notes in Computer Science, June, 90-95 (2001).
• M. H. Yang and N. Ahuja. Detecting huamn faces in color images. IEEE Proc. of Int. Conf. on Image Proc. (ICIP ’98), 1998.
• Nilamani Bhoi, Mihir Narayan Mohanty Matching based Eye Detection in Facial Image. International Journal of Computer Applications (0975 – 8887)Volume 12– No.5, December 2010.