人脸识别中遮挡区域恢复算法研究

计算机科学 ›› 2013, Vol. 40 ›› Issue (5): 307-310.

人脸识别中遮挡区域恢复算法研究

杜杏菁,郭明雄

北京理工大学光电学院光电成像技术与系统教育部重点实验室北京100081;华北科技学院计算机系燕郊065201

出版日期:2018-11-16 发布日期:2018-11-16

Research of Face Occlusion Recover Algorithm in Face Recognition

DU Xing-jing and GUO Ming-xiong

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 在分析脸部遮挡处理各算法的基础上,提出了自动多值掩模PCA人脸重建模型(MMPCA模型)。该模型首先进行特征提取,计算待测人脸和标准样本的特征脸差,判断遮挡部位,即遮挡类型；接着使用M估计器对遮挡掩模进行估计,为不同像素点估计符合自身特性的幅度参数,生成多值遮挡掩模；再通过3个半二次型函数迭代保证最优合成系数唯一与收敛,获得最优合成系数,重建人脸。实验结果表明,该算法能恢复遮挡部位,减弱遮挡对识别准确率的影响。

关键词: 人脸识别,遮挡恢复,多值掩模PCA人脸重建(MMPCA)

Abstract: Based on the analysis of facial occlusion handling various algorithms,a automatical multi-value mask PCA face reconstruction model (MMPCA model) was proposed．First the facial features are extracted,and the eigenface difference between a test face and a standard face is calculated to judge the facial occlusion accurately and determine the facal occlusion type.Then a occlusion mask is estimated with a M estimator,and the pixel’s amplitude parameters are estimated,and the multi-value occlusion mask is generated.Last three half secondary-type functions are used to ensure optimal synthesis coefficients is only and convergent,and then the optimal synthesis coefficient is obtained to reconstruct the face．The experimental results show that the occlusion region is restored and the occlusion influence to face recognition accuracy is weaken through using the automatical multi-value mask PCA face reconstruction model.

Key words: Face recognition,Occlusion recover,Multi-value mask PCA face reconstruction (MMPCA)

杜杏菁,郭明雄. 人脸识别中遮挡区域恢复算法研究[J]. 计算机科学, 2013, 40(5): 307-310. https://doi.org/

DU Xing-jing and GUO Ming-xiong. Research of Face Occlusion Recover Algorithm in Face Recognition[J]. Computer Science, 2013, 40(5): 307-310. https://doi.org/

参考文献

[1] 杜成,苏光大．用于人脸识别的正面人脸图像眼镜摘除[J]．清华大学学报:自然科学版,2005,5(7):928-930
[2] 王志明,陶建华．人脸遮挡区域检测与重建[J]．计算机研究与发展,2010,7(1):16-22
[3] Chenyu W,Ce L,Shu M．Automatic Eyeglasses Removal fromFace Images[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,6(30):322-336
[4] Colombo A,Cusana C,Schettini R．Detection and Restoration of Occlusions for 3D Face Recognition[C]∥IEEE International Conference on Multimedia and Expo．2006:1541-1544
[5] Smet M D,Fransens R,Gool L V．A Generalized EM Approach for 3D Model Based Face Recognition Under Occlusions[C]∥IEEE International Conference on Computer Vision and Pattern Recognition．2006:1423-1430
[6] Tsuda K,Ratsch G．Image Reconstruction by Linear Program-ming[J]．IEEE Transactions on Image Processing,2005,4(6):737-744
[7] Mo Z,Lewis J P,Neumann U．Face Inpainting with Local Linear Representations[C]∥Electronic Proceedings of British Machine Vision Conference．2004:399-407
[8] Zheng W S,Lai J H．Regularized Locality Preserving Learning of Pre image Problem in Kernel Principal Component Analysis[C]∥IEEE International Conference on Computer Vision and Pattern Recognition．2006:456-459
[9] 候鸿川．面部温谱图身份识别技术探讨[J]．中国人民公安大学学报,2005,3(3):17-21
[10] 陈雪蓉,敬忠良,孙邵缘．一种处理红外人脸识别中眼镜干扰的方法[J]．上海交通大学学报,2010,8(11):44-49
[11] 安高云．复杂条件人脸识别中的若干关键问题的研究[D]．北京:北京交通大学,2008
[12] Charbonnier P,Blanc-Feraud L,Aubert G．Deterninistic Edgepre-serving Regularization in Computed Imaging[J]．IEEE Transa-ctions on Image Processing,1997,6(2):298-311

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed