A Novel HOG Descriptor with Spatial Multi-Scale Feature for FER

Abstract:

HOG Feature is an efficient edge information descriptor, but it ignores the spatial arrangement of local FER features. In this respect, this paper puts forward a spatial multi-scale model based on an improved HOG algorithm which uses canny operator instead of traditional gradient operator. After the image is divided into a series of sub-regions layer by layer, the histogram of orient gradients for each sub-region is calculated and connected in sequence to obtain the spatial multi-scale HOG feature of whole image. Compared with traditional HOG and the improved PHOG, the proposed SMS_HOG algorithm acquires 5% recognition rate improvement and 50% processing time reduction.

• Periodical: Applied Mechanics and Materials (Volume 596)
• Pages: 322-327
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.596.322
• Online since: July 2014
• Authors: Ying Tong*, Liang Bao Jiao, Xue Hong Cao
• Keywords: Canny Gradient, Facial Expression Recognition, Histograms of Oriented Gradients, Spatial Multi-Scaled

References

[1] Mehrabian A. Communication without words[J]. Psychology Today, 1968, 2: 53~56.

[2] Marios Kyperountas, Anastasios Tefas, Ioannis Pitas. Salient feature and reliable classifier selection for facial expression classification [J]. Pattern Recognition, Vol. 43, 2010: 972-986.

DOI: 10.1016/j.patcog.2009.07.007

[3] Kobayashi T. BFO Meets HOG: Feature Extraction Based on Histograms of Oriented p. d. f. Gradients for Image Classification[C]. CVPR 2013: 747-754.

DOI: 10.1109/cvpr.2013.102

[4] M. Heikkilä,M. Pietikäinen,C. Schmid. Description of interest regions with local binary patterns[J]. Pattern Recognition, 2009, vol. 42, no. 3: 425–436.

DOI: 10.1016/j.patcog.2008.08.014

[5] Baochang Zhang, Yongsheng Gao, Sanqing Zhao, et al. Local Derivative Pattern Versus Local Binary Pattern: Face Recognition with High-Order Local Pattern Descriptor[J]. IEEE Transactions on Image Processing, 2010, Vol. 19, No. 2: 533-544.

DOI: 10.1109/tip.2009.2035882

[6] Zheng Yongbin, Huang Xinsheng, Feng Songjiang. An Image Matching Algorithm Based on Combination of SIFT and the Rotation Invariant LBP[J]. Journal of Computer 2 Aided Design & Computer Graphics, 2010 , Vol. 22, No. 2: 286-292.

[7] Xunyu Pan, Siwei Lyu. Detecting image region duplication using SIFT features[C]. ICASSP, 2010: 1706-1709.

[8] N Dala, B Triggs. Histograms of oriented gradients for human detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR05), San Diego, CA, USA, June 25-25, 2005: 886-893.

DOI: 10.1109/cvpr.2005.177

[9] Bosch A，Zisserman A，Munoz X. Representing shape with a spatial pyramid kernel [C]. International Conference on Image and Video Retrieval(CIVP'2007)，Amsterdam，Netherlands，July 9-11，2007：401-408.

DOI: 10.1145/1282280.1282340

[10] O. Déniz,G. Bueno,J. Salido, et al. Face recognition using Histograms of Oriented Gradients[J]. Pattern Recognition Letters, 2011, Vol. 32: 1598-1603.

DOI: 10.1016/j.patrec.2011.01.004

[11] Rodrigo Minetto, Nicolas Thome, Matthieu Cord, et al. T-HOG: An effective gradient-based descriptor for single line text regions[J]. Pattern Recognition, 2013, Vol. 46: 1078-1090.

DOI: 10.1016/j.patcog.2012.10.009