Open Journal Systems

Face Image Set Recognition Based on Improved HOG-NMF and Convolutional Neural Networks

Lixiu Hao, Weiwei Yu

Article ID: 14-24
Vol 2, Issue 1, 2019, Article identifier:

VIEWS - 221 (Abstract) 87 (PDF)


Objective Face recognition can be affected by unfavorable factors such as illumination, posture and expression, but the face image set is a collection of people’s various angles, different illuminations and even different expressions, which can effectively reduce these adverse effects and get higher face recognition rate. In order to make the face image set have higher recognition rate, a new method of combining face image set recognition is proposed, which combines an improved Histogram of Oriented Gradient (HOG) feature and Convolutional Neural Network (CNN). Method The method firstly segments the face images to be identified and performs HOG to extract features of the segmented images. Secondly, calculate the information entropy contained in each block as a weight coefficient of each block to form a new HOG features, and non-negative matrix factorization (NMF) is applied to reduce HOG features. Then the reduced-dimensional HOG features are modeled as image sets which keep your face details as much as possible. Finally, the modeled image sets are classified by using a convolutional neural network. Result The experimental results show that compared with the simple CNN method and the HOG-CNN method, the recognition rate of the method on the CMU PIE face set is increased by about 4%~10%. Conclusion The method proposed in this paper has more details of the face, overcomes the adverse effects, and improves the accuracy.


HOG; Non-negative matrix factorization; Convolutional Neural Network; Face image set recognition; Feature extraction

Full Text:



He C. A Survey of Face Recognition Technology [J]. Intelligent Computers and Applications 2016; 6(1): 112-114.

Dong XW, Yao SM, Wang YW, et al. Multi-manifold discrimination learning algorithm based on virtual sample image set[J]. Application Research of Computers 2018; 35(06): 1872-1878.

Zhang WK, Sun H, Sun X, Wang HQ. Visual Summary of Image Set Based on MFF-GAN [J]. Computer Engineering 2019; 45(02): 202-206.

Ren ZW, Wu MN. Image set classification algorithm based on entropy self-weighted joint regularization nearest point [J/OL]. computer application: 1-7 [2019-04-14].

Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection [C]. Computer Vision and Pattern Recognition 2005. Computer Society Conference on IEEE 2005: 886-893.

Xie Z, Jiang P, Zhang S. Fusion of LBP and HOG using multiplekernel learning for infrared face recognition [C]. IEEE/ACIS International Conference on Computer and Information Science 2017: 81-84.

Bhele SG, Mankar VH. Recognition of faces using discriminative features of LBP and HOG descriptor in varying environment [C]. International Conference on Computational Intelligence and Communication Networks 2016: 426-432.

Ghorbani M, Targhi AT, Dehshibi MM. HOG and LBP: Towards a robust face recognition system [C]. Tenth International Conference on Digital Information Management 2016: 138-141.

Sun R, Chen J, Gao W. A Fast Pedestrian Detection Method Based on Significance Detection and HOG-NMF Features [J]. Journal of Electronics & Information Technology 2013; 35(08): 1921-1926.

Lin KZ, Zhang YM, Li YT. Research on HOG feature extraction algorithm based on information entropy weighting [J/OL]. computer engineering and applications: 1-10 [2019-05-06].

Wang HB, Chen YX, Li YQ. Face recognition method based on principal component analysis and Softmax regression model [J]. Journal of Hefei University of Technology (Natural Science) 2015; 38(06): 759-763.

Zhang YM. Research on Face Recognition Algorithm Based on HOG and Gabor Features [D]. Harbin University of Science and Technology 2019.

Lee H, Yoo J, Choi S. Semi-supervised nonnegative matrix factorization [J]. IEEE Signal Processing Letters 2010; 17(1): 4-7.

Syafeeza AR, Khalil-Hani M, Liew SS, et al. Convolutional neural network for face recognition with pose and illumination variation [J]. International Journal of Computational Intelligerce & Applications 2015; 14(3): 1-18.

Hou XP, Gao Y. Application of Convolutional Neural Network CNN Algorithm in Text Classification [J]. Technology and Innovation 2019(04): 158-159.

(221 Abstract Views, 87 PDF Downloads)


  • There are currently no refbacks.

Copyright (c) 2019 Lixiu Hao, Weiwei Yu

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.