Computer Science ›› 2017, Vol. 44 ›› Issue (1): 303-307.doi: 10.11896/j.issn.1002-137X.2017.01.056

Previous Articles     Next Articles

Improved HOG Face Feature Extraction Algorithm Based on Haar Characteristics

JIANG Zheng and CHENG Chun-ling   

  • Online:2018-11-13 Published:2018-11-13

Abstract: Most of existing feature extraction algorithms are prone to be influenced by external factors such as illumination,which can lead to the decrease of face recognition rate.The robustness of histogram of oriented gradient (HOG) can solve the problem that brought by illumination on face recognition rate.However,when calculating the gradient direction and amplitude of pixels,the traditional HOG algorithm considers only the impact of the four pixels situated in horizontal and vertical direction.The gradient direction and amplitude of pixels may become unstable when the external environment changes.Thus,we proposed an improved HOG face feature extraction algorithm based on Haar characteris-tics.When calculating the gradient direction and amplitude,we considered the influence of 8 pixels.Meanwhile,because of the simple and fast operating of Haar-like features,we inducted Haar into HOG.We showed four groups of Haar feature encoding models,which calculated the texture features of face according to the improved HOG.In our experiments we used FERET and Yale B datasets.Experiments demonstrate that,compared with existing algorithms,the proposed method has better robustness and improve the recognition rate under varying illumination conditions.On the fb,fc,dup1 and dup2 datasets,the recognition rates of the proposed method are 95.1%,80.9%,70.1% and 63.2% respectively.On the Yale B datasets,its rate is 89.1%.

Key words: Feature extraction,Face recognition,HOG,Haar,Encoding model

[1] TAN Heng-liang,YANG Bing,MA Zheng-ming.Face recognition based on the fusion of global and local HOG features of face images [J].IET Computer Vision,2014,8(3):224-234.
[2] CHELALI,ZOHRA F,DJERADI,et al.Face recognition system using Discrete cosine transform combined with MLP and RBF neural networks [J].International Journal of Mobile Computing and Multimedia Communications,2012,4(4):11-35.
[3] HAFEDZ M,LEVINE M D.Face recognition using the discrete cosine transform [J].International Journal of Computer Vision,2001,43(3):167-188.
[4] DORNAIKA F,ASSOUM A.Enhanced and parameterless locality preserving projections for face recognition [J].Neurocomputing,2013,99:448-457.
[5] TURK M,PENTLAND A.Face recognition using eigenfaces[C]∥IEEE Conference on Computer Vision and Pattern Recognition.1991:586-590.
[6] BELHUMEUR P N,HESPANHA J P,KRIEGMAN D J.Ei-genfaces against Fisherfaces:recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[7] YI Jun,SU Fei.Histogram of Log-Gabor Magnitude Patternsfor face recognition [C]∥IEEE International conference on Speech and Signal Processing(ICASSP).2014:519-523.
[8] SHAN Shi-guang.Study on key issuses in face recognition[D].Beijing:Institute of Computer Technology,Chinese Academy of Science,2004.(in Chinese) 山世光.人脸识别中若干关键问题的研究[D].北京:中国科学院计算机技术研究所,2004.
[9] FAUDZI S,YAHYA N.Evaluation of LBP-based face recognition techniques [C]∥International Conference on Intelligent and Advanced Systems(ICIAS).2014:1-6.
[10] CHEN Dong,CAO Xu-dong,WEN Fang,et al.Higher is better:high-dimensional feature and its efficient compression for face verification [C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2013:1-8.
[11] LU Jian-yun,HE Zhong-shi,YU Lei.A face recognition method based on the fusion of multi-level center-symmetric local binary pattern features[J].Computer Engineering and Science,2010,32(6):48-51.(in Chinese) 卢建云,何中市,余磊.基于多级CS-LBP特征融合的人脸识别方法[J].计算机工程与科学,2010,32(6):48-51.
[12] NANNI L,BRAHNAM S,LUMINI A.A local approach based on a local binary patterns variant texture descriptor for classifying pain states [J].Expert Systems with Applications,2010,7(12):7888-7894.
[13] PANG Yan-wei,YUAN Yuan,LI Xue-long,et al.Efficient HOGhuman detection[J].Signal Processing,2011,1(4):773-781.
[14] YU Jing,QIN Zeng-chang,WAN Tao,et al.Feature integration analysis of bag-of-features model for image retrieval[J].Neuron computing,2013,120(23):355-364.
[15] THANH-TOAN Do,KIJAKE.Face recognition using co-occurrence histograms of oriented gradients[C]∥International Conference on Speech and Signal Processing(ICASSP).2012:1301-1304.
[16] YANG Bing,WANG Xiao-hua,YANG Xin.Face recognition me-thod based on HOG pyramid[J].Journal of Zhejiang University,2014,48(9):1564-1569.(in Chinese) 杨冰,王小华,杨鑫.基于HOG金字塔人脸识别方法[J].浙江大学学报,2014,48(9):1564-1569.
[17] GUO Jin-xin,CHEN Wei.Face recognition based on multi-feature fusion and random forest[J].Computer Science,2013,40(10):279-283.(in Chinese) 郭金鑫,陈玮.基于HOG多特征融合与随机森林的人脸识别[J].计算机科学,2013,40(10):279-283.
[18] CHEN Rui,PENG Qi-min.Pedestrian detection based on HOG of stable area[J].Journal of Computer-Aided Design and Computer Graphics,2012,4(3):372-377.(in Chinese) 陈锐,彭启民.基于稳定区域梯度方向直方图的行人检测方法[J].计算机辅助设计与图形学报,2012,24(3):372-377.
[19] SUN Jun-ding,ZHAO Shan.Image bottom feature extractionand retrieval technology[M].Beijing:Electronic Industry Press,2009:112-115.(in Chinese) 孙君顶,赵珊.图像底层特征提取与检索技术[M].北京:电子工业出版社,2009:112-115.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!