计算机科学 ›› 2018, Vol. 45 ›› Issue (6): 308-313.doi: 10.11896/j.issn.1002-137X.2018.06.054
所属专题: 人脸识别
钟锐1,2, 吴怀宇1, 何云1
ZHONG Rui1,2, WU Huai-yu1, HE Yun1
摘要: 传统的人脸识别模型采用离线方式进行训练,同时由于人脸特征维数较高导致算法的实时性不足。文中分别从人脸特征与分类器两方面来构建快速的人脸识别算法。首先使用SDM(Supervised Descent Method)算法进行人脸特征点定位,提取每个人脸特征点邻域内的局部(Multi Block-Center Symmetric Local Binary Patterns,MB-CSLBP)特征,并将所有的人脸特征点邻域特征以串联的方式构成局部融合特征,即所提出的局部融合MB-CSLBP特征LFP-MB-CSLBP(Local Fusion Feature of MB-CSLBP)。将以上特征送入分层增量树HI-tree(Hierarchical Incremental tree)中进行人脸识别模型的在线训练。分层增量树是使用分层聚类算法来实现增量式学习的,因此其能够以在线的方式对识别模型进行训练,具有较高的实时性与准确性。最后在3种不同的人脸库以及摄像头采集的人脸视频上对算法的识别率与实时性进行测试。实验结果表明,相比于当前其他算法,所提算法具有较高的人脸识别率与实时性。
中图分类号:
[1]BECKER B C,ORTIZ E G.Evaluating open-universe face identification on the Web[C]//IEEE Conference on Computer Vision and Pattern Recognition.2013:904-911. [2]KAHRAMAN F,KURT B,GOKMEN M.Robust face alignment for illumination and pose invariant face recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.2007:1-7. [3]MEDIONI G,CHOI J,KUO C H,et al.Identifying noncooperative subjects at a distance using face images and inferred three dimensional face models[J].IEEE Transactionson Systems Man & Cybernetics Part A Systems & Humans,2009,39(1):12-24. [4]LIOR W,TAL H,YANIV T.Effective unconstrained face recognition by combining multiple descriptors and learned background statistics[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(10):1978-1990. [5]CHEN D,CAO X,WIPF D,et al.An Efficient Joint Formulation for Bayesian Face Verification[J].IEEE Transactions.on Pattern Analysis and Machine Intelligence,2017,39(1):32-46. [6]LI P,MOHAMMED U,ELDER J,et al.Probabilistic Models for Inference about Identity[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):144-157. [7]MOGHADDAM B,JEBARA T,PENTLAND A.Bayesian face recognition[J].Pattern Recognition,2000,33(11):1771-1782. [8]CHEN D,CAO X,WEN F,et al.Blessing of Dimensionality:High-Dimensional Feature and Its Efficient Compression for Face Verification[C]//IEEE Conference on Computer Vision and Pattern Recognition.2013:3025-3032. [9]TAN H,YANG B,MA Z.Face recognition based on the fusion of global and local HOG features of face images[J].IET Computer Vision,2014,8(3):224-234. [10]ARASHLOO S R,KITTLER J.Class-Specific Kernel Fusion of Multiple Descriptors for Face Verification Using Multiscale Binarised Statistical Image Features[J].IEEE Transactions on Information Forensics and Security,2014,9(12):2100-2109. [11]LIANG Q X,HE G H,CHEN R L,et al.Research of face recognition algorithm based on nonnegative tensorfactorization[J].Computer Science,2016,43(10):312-316.(in Chinese) 梁秋霞,何光辉,陈如丽,等.基于非负张量分解的人脸识别算法研究[J].计算机科学,2016,43(10):312-316. [12]WENG J Y,HWANG W S.Incremental Hierarchical Discriminant Regression[J].IEEE Transactionson on Neural Networks,2007,18(2):397-415. [13]XIONG X H,TORRE F.Supervised Descent Method and Its Application to Face Alignment[C]//IEEE Conference on Computer Vision and Pattern Recognition.2013:532-539. [14]HUANG G B,MATTAR M,BERG T,et al.Labeled faces in the wild:a database for studying face recognition in unconstrained environments[J].International Journal of Computer Vision,2007,96(3):277-279. [15]SIM T,BAKER S,BSAT M.The CMU pose,illumination and expression database[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(12):1615-1618. [16]GEORGHIADESA S,BELHUMEUR P N,KRIEGMAN D J,et al.From few to many:illumination cone models for face recognition under variable lighting and pose[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):643-660. [17]ZHANG K,ZHANG L,YANG M H.Real-time compressive tracking[C]//European Conference on Computer Vision.2012:864-877. |
[1] | 丁剑,王树英. 一种使用shapelets的增量式时间序列分类 Incremental Time Series Classification Algorithm Based on Shapelets 计算机科学, 2016, 43(5): 257-260. https://doi.org/10.11896/j.issn.1002-137X.2016.05.048 |
|