Face Detection with Facial Features and Gender Classification Based On Support Vector Machine

Abstract This paper presents a novel face detection and gender classification strategy in color images under nonuniform background. This is done by detecting the human skin regions in image given and detecting facial features based on the measurements in pixels. The proposed algorithm converts the RGB image into the YCbCr color space to detect the skin regions in the facial image. But in order to detect facial features the color image is converted in to gray scale image. This method locates the lip region and the mouth region. From this, left and right eyes’ and the nose regions are located. The gender classification method classifies almost all the images with different image sizes. The best classification rate is achieved using Linear Support Vector Machine. .