量子电子学报, 2015, 32 (3): 270, 网络出版: 2015-05-29
利用FW-PCA检测遮挡区域的人脸识别
Robust face recognition by using FW-PCA detecting occluded region
图像处理 人脸识别 遮挡区域检测 快速加权PCA 相位相关算法 局部二值模式 image processing face recognition occluded region detecting fast-weighted principal component analysis phase-only correlation local binary pattern
摘要
针对人脸识别中存在遮挡而影响识别性能的问题,提出了一种利用快速加权主成分分析(FW-PCA),检测遮 挡区域的鲁棒人脸识别算法。利用FW-PCA检测输入图像的遮挡区域,将其与图库图像的遮挡 区域进行比较;利用局部二值模式匹配确定最优权重系数,利用相位相关算法匹配确定遮挡掩码; 计算每个测试图像的匹配得分,并利用最近邻分类器完成人脸识别。在FRGC2和UND人脸库上的实验 结果表明,此算法的识别率可高达99.6%,相比其他几种较新的人脸识别算法,取得了更好的识别性能。
Abstract
For the issue that performance of face recognition algorithms was impacted by occlusion, a robust face recognition algorithm by using fast-weighted principal component analysis (FW-PCA) detecting occluded region was proposed. FW-PCA was used to detect occluded region, and occluded region of input images were compared with gallery images. Local binary pattern (LBP) was used to determine the optimal weights and phase-only correlation (POC) was used to get occluded mask. Matching score of each image was calculated, face recognition was finished by nearest neighbor classifier. Experimental results on FRGC2 and UND show that the recognition accuracy can achieve 99.6%. It has better recognition performance than several advanced recognition algorithms.
乔蕊, 李靖. 利用FW-PCA检测遮挡区域的人脸识别[J]. 量子电子学报, 2015, 32(3): 270. QIAO Rui, LI Jing. Robust face recognition by using FW-PCA detecting occluded region[J]. Chinese Journal of Quantum Electronics, 2015, 32(3): 270.