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。
[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 |
No related articles found! |
|