基于区域块LBP特征的人脸表情识别

Human Face Recognition Based on the Regional Block LBP

人脸表情识别是模式识别与人工智能领域的研究热点之一,针对传统LBP方法的不足,提出了一种基于区域块LBP的人脸表情识别方法:先在人脸面部分割出与表情相关的眉毛、眼睛、鼻子和嘴巴等关键区域;再从这些关键表情区域提取表情特征,避免了在整个面部提取特征耗时的缺陷,同时有效地降低了特征维数;最后利用最近邻分类器给出识别结果,通过实验验证了本文算法在识别性能和时间性能上的优势。

Facial expression describes human emotion by obviously and embody in facial features. Facial expression recognition has attracted more and more attention of researchers,and it has become a hot research topic in the fields of pattern recognition and artificial intelligence in recent years. Aiming at the shortage of the traditional LBP method,this paper proposes a new method of facial expression recognition based on block LBP. First,we divide the expression regions on the whole face,such as eyebrows,eye,nose and mouth,then extract the facial expression feature in the key regions,so avoid time-consuming defects in the entire face extraction and reduce the feature dimension effectively. Last,this paper gives the recognition results by the nearest neighbor classifier. The relevant experiments indicate that this algorithm achieves good results in recognition performance and time performance.