Face detection system using HSV color model and morphing operations

Abstract

Skin detection is the process of finding skin-colored pixels and regions in a given image. This process is typically used as a pre-processing step to find regions that potentially have human faces in images. Several computer vision approaches have been developed for skin detection. A variety of color space model are on shelf for deployment. A simple face detection procedure which has two major steps, first to segment skin region from an image, and second, to decide these regions contain human face or not. The procedure is based on skin color segmentation and human face features (knowledge-based approach. For skin color segmentation HSV color model has been used. Various color space model along with threshold, helps to remove non-skin like pixels from an image. Later tested each skin region, that skin region is actually represents a human face or not. Further the morphological operations are used to smooth the object boundary without changing their respective area based on shapes. Operations such as erosion, dilation are used to execute the process of face detection which improves the efficiency rate.