摘要
提出一种联合局部三值模式(LTP)和局部相位量化(LPQ)的人脸识别方法,该方法首先对预处理后的人脸分别采用LTP算子、LPQ算子提取各自的直方图,然后,通过特征选择将两者联合为LTP_LPQ直方图,最后通过最近邻分类器进行分类识别。在ORL和YALE标准人脸数据库上的实验表明,该方法能有效地提高人脸的识别率。
A method of face recognition based on local ternary pattern(LTP)and local phase quantization(LPQ)was proposed.Firstly,each histogram by LTP operator and LPQ operator was extracted respectively based on the pretreated faces,then both histograms were fused into the LBP_LPQ histogram by feature selection,finally they were identified by the nearest neighbor classifier.Experiments based on the ORL and YALE standard face database illustrated that this method can effectively improve the recognition rate of face.
出处
《计算机与数字工程》
2014年第12期2396-2398,2414,共4页
Computer & Digital Engineering
关键词
人脸识别
局部二值模式
局部三值模式
局部相位量化
face recognition
local binary pattern
local ternary pattern
local phase quantization