|
|
|
| HOG-NPE: A Novel Local Description Operator for Face Image Recognition |
| Dezhou University, Dezhou, Shandong 253023, China |
|
|
|
Abstract The method of extracting robust feature sets from an image is a crucial issue for the areas of computer
vision and pattern recognition. The nature of real data is a very high dimensional data. However, the
hidden structure can be well characterized by a small number of features in most cases. As a result,
the method of extracting a small number of good features is an important question in computer vision
and pattern recognition, etc. We employ the Histograms of Oriented Gradient (HOG) to extract the
robust feature sets of facial images, which is a local description operator that possesses a certain degree
of invariance against geometric and photometric deformations. Neighborhood Preserving Embedding
(NPE) which is a subspace learning algorithm is adopted to extract a small number of good features on
the local description operators. We use the novel local description operator - HOG-NPE for facial image
recognition, and several experiments on well-known facial databases are conducted, which demonstrate
good performance and effectiveness of this novel local description operator.
|
|
|
| Fund:
Project supported by Natural Science Foundation of Shandong (No. ZR2012AM008).
|
|
|
|
| Cite this article: |
|
Hongfeng Wang. HOG-NPE: A Novel Local Description Operator for Face Image Recognition[J]. Journal of Fiber Bioengineering and Informatics, 2014, 7(3): 419-427.
|
|
[1] Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. IEEE Com-
puter Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, 2005, 1:
886-893.
[2] He XF, Cai D, Yan SC, Zhang HJ. Neighborhood preserving embedding. IEEE International
Conference on Computer Vision, ICCV 2005, 2005, 2: 1208-1213.
[3] Jiang XY, Zhou XH,Weng M, Zheng JJ, Jiang YX. Image processing techniques and its application
in water transport through fabrics. J. Fiber Bioengineering Informatics, Vol. 3, No. 2, Sept 2010.
pp. 88-93
[4] Sun C, Zheng R, Li J, Huang HQ , Cui MH. Image perception of female breast beauty and its
relation to 3D anthropometric measurements. J. Fiber Bioengineering Informatics, Vol. 4, No. 1,
Apr. 2011. pp. 23-34
[5] Li PF, Jiao Y, Jing JF, Li JN. The high-speed fabric defect detection algorithm based on the
image layered model. Journal of Fiber Bioengineering & Informatics 6: 2 (2013) 161-173.
[6] Cai D, He XF, Han JW, Zhang HJ. Orthogonal laplacianfaces for face recognition. IEEE Trans-
actions on Image Processing, 2006, 15(11): 3608-3614.
[7] Cai D, He XF, Zhou K. Locality sensitive discriminant Analysis. IJCAI. 2007: 708-713.
[8] Cai D, He XF, Han JW. Semi-supervised discriminant analysis. IEEE 11th International Confer-
ence on Computer Vision, ICCV 2007, 2007: 1-7.
[9] Wang QJ, Zhang RB. LPP-HOG: A new local image descriptor for fast human detection. IEEE
International Symposium on Knowledge Acquisition and Modeling Workshop, 2008: 640-643.
[10] Zhu, Qiang, et al. Fast human detection using a cascade of histograms of oriented gradients.
Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. Vol. 2.
IEEE, 2006.
[11] Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. Science,
2000, 290(5500): 2323-2326.
[12] http://cvc.yale.edu/projects/yalefaces/yalefaces.html
[13] http://vision.ucsd.edu/leekc/ExtYaleDatabase/ExtYaleB.html |
|
|
|
2014, Vol. 7 
