Frontal Face Detection Using Edge Projections



In this project, a frontal face detection method in images and video is developed. After determining possible face candidate regions using color information, each region is filtered by a high-pass filter of a wavelet transform. In this way, edges of the region are highlighted, and a caricature-like representation of candidate region is obtained. Horizontal, vertical and filter-like projections of the region are used as feature signals in support vector machine (SVM) based classifiers. It is experimentally observed that our face detection method provides promising results for both image and video processing applications.


Below are some example screen-shots of our frontal face detection software.





_Source Code_

Source code can be downloaded from here (zip file).


This software is developed at the Department of Electrical and Electronics Engineering at Bilkent University, Turkey, under the supervision of Prof. A. Enis Cetin who was an Associate Editor of IEEE Transactions on Image Processing between 1999 and 2003, and now he is an Associate Editor of Journal of Applied Signal Processing. Please contact him, if you are interested in this software.


Here is the link for eye-localization algorithm using edge-projections.