基于局部Shearlet相位量化特征的人脸识别算法  

The Face Recognition Based on Local Shearlet Phase Quantization

作　　者：王宪[1] 秦磊[1] 孙子文[1] 宋书林[1] 丁志涵[1] 

机构地区：[1]轻工过程先进控制教育部重点实验室(江南大学),江苏无锡214122

出　　处：《光电工程》2013年第4期106-112,共7页Opto-Electronic Engineering

基　　金：国家自然科学基金(60574051);江苏省产学研联合创新资金-前瞻性联合研究项目(BY2012067)

摘　　要：针对LPQ算子提取的纹理特征易受光照、噪声影响,提出了一种在Shearlet变换幅值域内提取局部相位量化标记直方图的人脸描述方法。首先采用Shearlet滤波器提取其对应不同方向、不同尺度的多个Shearlet幅值域图谱,然后按照平均值融合法将相同尺度不同方向的幅值域图谱融合到一起,并对融合图谱进行分块,分别采用LPQ算子标记幅值域图谱,最后由这些标记直方图形成的序列来描述人脸。在ORL、FERET和YALE人脸库中做了多组实验并分别取得了98%、95%及97.33%的识别率,充分验证了该方法的有效性。Since the original Local Phase Quantization （LPQ） operator has a poor performance in extracting the texture features under illumination or noise effect, a method of face description is proposed which extracts the histogram sequence of Local Shearlet Phase Quantization （HLSPQ） from the magnitudes of Shearlet coefficients. First, In order to extract the multi-orientation information, the average fusion method is proposed to fuse the original Shearlet features of the same scale. Second, the fused image is divided into several units from which the local phase quantization operates is used to extract the local neighbor patterns. Then, the LPQ operates on each unit to extract the local neighbor patterns. Finally, the input face image is described by the histogram sequence extracted from all these region patterns. The experimental results on ORL, FERET and YALE face database can achieve high face recognition rate up to 98%, 95% and 97.78%, which shows that the proposed method has better effect on improving the recognition rate.

关 键 词：SHEARLET变换 特征融合 局部相位量化 多尺度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]