Race identification from facial images using statistical techniques

Abstract

The main aim of this paper is to determine the skin of the person from his/her face given in their respective images. Skin color is a distinguishing feature of human faces. Skin detection has also been used to locate body limbs, such as hands, as a part of hand segmentation and tracking systems etc. Application where skin discovery was utilized to distinguish stays, correspondents in TV news recordings for video programmed clarification, chronicled, and recovery. In such an application, it is usual that the face and the hands of the anchor/reporter person are the largest skin-tone colored region in a given frame since, typically, diverse new sorts of projects are shot in roofed situations with man-made foundation materials that barely contain skin-hued objects. To achieve the above task it is very important to be able to detect the face of the person which has its own various real-life applications such as video surveillance and face image database management etc.

This paper mainly displays the color code of the skin tone of the detected face. It utilizes the Open CV library functions and HARR file which contains frontal feature information, which forms the base for face detection and ultimately for skin tone detection. It works on producing nearby accurate results i.e., nearly correct color code of the skin tone of the given image.

Keywords:

• Skin tone colored ,Open CV
• library
• video programmed
• HARR file
• skin hued objects

Mathematics Subject Classification 2010:

• 62H35