Face Detection Method Based on Skin Color Segmentation and Eyes Verification

Abstract

Due to the existence of complicated illumination, background and variations of pose, fast and robust face detection is constrainted in many applications. This paper describes a novel scheme conceived to integrate multiple cues to detect face under in-plane rotation, Concretely, we apply skin-color, heuristic rules and eye feature to build a robust detector. First, skin detection approach based on novel skin color model is applied to search potential face regions. Then, In order to reduce the number of candidates furtherly, major distinct non-face candidates are filtered out via prejudging rules. Next, eye localization is carried out to verify true face in remained candidates. For the purpose of finding eyes precisely, localization utilizes several methods including of EyeMap, illumination correction, template matching. Finally, we can achieve orientation and rotation face by using of eye-pair size and position. Evaluated by our own facial images and videos with complicated illumination and background, the system has high calculation speed, illumination independency as well as pose insensitivity, and obtains good experimental results.