Facial expression recognition based on local gradient DT-CWT dominant direction pattern
Author:
Affiliation:

1. Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, Hefei University of Technology, Hefei 230009, China; 2. School of Electronic Science and Applied Physics, Hefei University of Technology, Hefei 230009, China; 3.South China University of Technology, Guangzhou 510006, China

Clc Number:

TP391;TN911

  • Article
  • | |
  • Metrics
  • |
  • Reference [20]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    A novel facial expression recognition is proposed in the paper, in which the local gradient dualtree complex wavelet transform dominant direction pattern is used. Firstly, four layers DTCWT are used on normalized expression image. For each layer, we can obtain the feature images of eight directions, which include 6 highfrequency directions and 2 lowfrequency directions. A new DDP (IDDP) is constructed, and which is used to code for each DTCWT feature image. Secondly, the IDDP feature images of each layer in different directions are fused based on rules of gradient direction, and every fused image is divided into several nonoverlapping and equalsized blocks. The corresponding histogram of the fused feature in each block is calculated respectively, and the final feature of facial expression image is obtained by cascading all of them. Finally, the nearest neighbor method based on Chi Square statistic weighted by Fisher is used to classify and identify. A large number of experiments show that the proposed method has a certain advantage on the recognition rate and recognition time.

    Reference
    [1]胡步发, 王金伟. 双模态及语义知识的三维人脸表情识别方法[J]. 仪器仪表学报, 2013, 34(4):873880. HU B F, WANG J W. 3D facial expression recognition method based on bimodal and semantic knowledge[J]. Chinese Journal of Scientific Instrument, 2013, 34(4):873880.
    [2]ELEFTHERIADIS S, RUDOVIC O, PANTIC M. Discriminative shared Gaussian processes for multiview and viewinvariant facial expression recognition[J]. IEEE Transactions on Image Processing, 2015, 24(1):189204.
    [3]於俊, 汪增福, 李睿. 一种同步人脸运动跟踪与表情识别算法[J]. 电子学报,2015,43(2):371376. YU J, WANG Z F, LI R. A simultaneous facial motion tracking and expression recognition algorithm[J]. Acta Electronica Sinica, 2015,43(2): 371376.
    [4]ZHANG W, ZHANG Y, MA L, et al. Multimodal learning for facial expression recognition[J]. Pattern Recognition, 2015, 48(10):31913202.
    [5]胡敏, 李堃, 王晓华,等. 基于直方图加权HCBP的人脸表情识别[J]. 电子测量与仪器学报, 2015, 29(7):953960. HU M, LI K, WANG X H, et al. Facial expression recognition based on histogram weighted HCBP[J]. Journal of Electronic Measurement and Instrumentation, 2015, 29(7):953960.
    [6]GU W, XIANG C, VENKATESH Y V, et al. Facial expression recognition using radial encoding of local Gabor features and classifier synthesis[J]. Pattern Recognition, 2012, 45(1):8091.
    [7]李雅倩, 李颖杰, 李海滨,等. 融合全局与局部多样性特征的人脸表情识别[J]. 光学学报, 2014,34(5):17. LI Y Q, LI Y J, LI H B, et al. Fusion of global and local various feature for facial expression recognition[J]. Acta Optica Sinica, 2014,34(5):17.
    [8]王晓华, 黄伟, 金超,等. 多特征多分类器优化匹配的人脸表情识别[J]. 光电工程, 2016, 43(3):7379. WANG X H, HUANG W, JIN CH, et al. Facial expression recognition based on the optimal matching of multifeature and multiclassifier[J]. OptoElectronic Engineering, 2016, 43(3):7379.
    [9]ZHENG W, LIU C. Facial expression recognition based on texture and shape[C]. 25th Wireless and Optical Communication Conference (WOCC), IEEE, 2016: 15.
    [10]刘帅师, 田彦涛, 万川. 基于Gabor多方向特征融合与分块直方图的人脸表情识别方法[J]. 自动化学报, 2011,37(12):14551463. LIU SH SH, TIAN Y T, WAN C. Facial expression recognition method based on Gabor multiorientation features fusion and block histogram[J]. Acta Automatica Sinica, 2011, 37(12):14551463.
    [11]马本学, 高国刚, 王宝,等. 基于双树复小波变换和邻域操作的哈密瓜纹理提取[J]. 农业机械学报, 2014, 45(12):316322. MA B X, GAO G G, WANG B, et al. Texture exrtaction of Hami Melon on dual tree complex wavelet transform and neighborhood operation[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(12): 316322.
    [12]王仕民, 叶继华, 邓涛,等. 2维双树复小波不确定度加权融合的人脸识别[J]. 中国图象图形学报,2012, 17(8):9951001. WANG SH M, YE J H, DENG T, et al. Twodimensional dualtree complex wavelet transform uncertainty weighted fusion in face recognition[J]. Journal of Image & Graphics, 2012, 17(8):9951001.
    [13]LIU J, JING X, SUN S, et al. Local Gabor dominant direction pattern for face recognition[J]. Chinese Journal of Electronics, 2015, 24(2):245250.
    [14]宋怡焕, 饶秀勤, 应义斌. 基于DTCWT和LSSVM的苹果果梗/花萼和缺陷识别[J]. 农业工程学报, 2012, 28(9):114118. SONG Y H, RAO X Q, YING Y B. Apple stem/calyx and defect discrimination using DTCWT and LSSVM[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(9): 114118.
    [15]杨飞, 苏剑波. 人脸显性特征的融合构造方法及识别[J]. 电子学报, 2012, 40(3):466471. YANG F, SU J B. Face recognition based on explicit facial features by fusion construction method[J]. Acta Electronica Sinica, 2012, 40(3):466471.
    [16]孙东辉, 鞠秀亮, 冯登超,等. 基于FAST检测器和SURF描述子的聚合图像人脸识别[J]. 国外电子测量技术, 2016, 35(1):9498. SUN D H, JU X L,FENG D CH, et al. Aggregated image face based on Fast detection and SURF descriptor[J]. Foreign Elecrronic Measurement Technology, 2016, 35(1):9498.
    [17]KINGSBURY N. Image processing with complex wavelets[J]. Philosophical Transactions of the Royal Society of London A Mathematical Physical & Engineering Sciences, 1999, 357(1760):25432560.
    [18]蔡蕾, 张春雨, 李斌,等. 基于Qshift双树复数小波系数的纹理图像检索[J]. 光电子·激光, 2009, 20(9):12521257. CAI L, ZHANG CH Y, LI B, et al. Texture image retrieval based on the statistical model of Qshift dualtree complex wavelet coefficients[J]. Journal of Optoelectronics Laser, 2009, 20(9):12521257.
    [19]KENNEL P, BORIANNE P, SUBSOL G. An automated method for treering delineation based on active contours guided by DTCWT complex coefficients in photographic images: Application to Abies alba, wood slice images[J]. Computers & Electronics in Agriculture, 2015, 118(C):204214.
    [20]李伟芳,滕奇志,汪华章.基于分块直方图和共生矩阵的图像检索方法[J].电子测量技术,2009,32(1):14. LI W F, TENG Q ZH, WANG H ZH. Image retrieval based on blocked histograms and cooccurrence matrix[J]. Electronic Measurement Technology, 2009,32(1):14.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Online: July 26,2017
Article QR Code