基于多块局部二值模式特征和人眼定位的人脸检测

Face detection based on MB-LBP and eye tracking

人脸检测是人脸识别和重构问题中最基本的任务,同样也是人脸识别问题中的一个关键环节,其结果直接关乎到人脸识别最终的效果。所以,构建一种稳健而优秀的检测算法是人脸检测的目的。本文提出了一种基于多块局部二值模式特征的adaboost算法和模板匹配的人眼定位方法,从而提高人脸检测的正确率和稳定率,减少了误差。通过MIT CBCL人脸数据库、生活、网络等渠道照片的实验验证,该方法提高了检测效率,降低误检率,兼具了实时性和鲁棒性。

Face detection is not only a basic task for face recognition and reconstruction, but also is the key section of face recognition system. The result of face detection has important influence on the effect of face recognition. It is necessary to build an excellent face detection algorithm. The face detection method based on MB-LBP and eye tracking is presented. Experimental result shows that the method not only enhances the accuracy and robustness, but also reduces the false alarm rate and operation time.