Improved Anchored Neighborhood Regression Enhancement for Face Recognition

doi:10.1007/s12204-018-1989-7

Abstract

Abstract: Although progress in face recognition is encouraging, the accuracy rate of face recognition remains to be increased. Since the face image quality has a positive influence on face recognition accuracy, the image enhancement methods are popular in face recognition. Most current image enhancement methods aim at improving visual appearance, but cannot improve recognition accuracy remarkably. In this paper, a feature evaluation operator is designed to overcome this problem. The operator selects patches with the best quality, and then face image is reconstructed with the selected patches. The proposed algorithm is tested on two different face recognition applications. Accuracy is raised after enhancement, and the result proves that the proposed algorithm is effective.

Key words: enhancement| anchored neighborhood regression (ANR)| recognition accuracy| feature evaluation operator

摘要： Although progress in face recognition is encouraging, the accuracy rate of face recognition remains to be increased. Since the face image quality has a positive influence on face recognition accuracy, the image enhancement methods are popular in face recognition. Most current image enhancement methods aim at improving visual appearance, but cannot improve recognition accuracy remarkably. In this paper, a feature evaluation operator is designed to overcome this problem. The operator selects patches with the best quality, and then face image is reconstructed with the selected patches. The proposed algorithm is tested on two different face recognition applications. Accuracy is raised after enhancement, and the result proves that the proposed algorithm is effective.

关键词: enhancement| anchored neighborhood regression (ANR)| recognition accuracy| feature evaluation operator

CLC Number:

TP 391

WANG Yunfei (王云飞), DING Hui (丁辉), SHANG Yuanyuan (尚媛园), SHAO Zhuhong (邵珠宏), FU Xiaoyan (付小雁). Improved Anchored Neighborhood Regression Enhancement for Face Recognition[J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(5): 600-606.

References 17

[1]	LIU C, SHUM H Y, FREEMAN W T. Face hallucination:Theory and practice [J]. International Journal of Computer Vision, 2007, 75(1): 115-134.
[2]	GAO X F, LI S Z, LIU R, et al. Standardization of faceimage sample quality [C]//Proceedings of 2nd InternationalConference on Biometrics. Berlin, Germany:Springer, 2007: 242-251.
[3]	AGARWAL T K, TIWARI M, LAMBA S S. Modifiedhistogram based contrast enhancement usinghomomorphic filtering for medical images [C]//2014IEEE International Advance Computing Conference(IACC). Piscataway, USA: IEEE, 2014: 964-968.
[4]	MAINI R, AGGARWAL H. A comprehensive reviewof image enhancement techniques [J]. Journal of Computing,2010, 2(3): 8-13.
[5]	PROTTER M, ELAD M, TAKEDA H, et al. Generalizingthe nonlocal-means to super-resolution reconstruction[J]. IEEE Transactions on Image Processing,2009, 18(1): 36-51.
[6]	WANG X G, TANG X O. Hallucinating face by eigentransformation[J]. IEEE Transactions on Systems,Man, and Cybernetics, Part C (Applications and Reviews),2005, 35(3): 425-434.
[7]	RANI A, KAUR G. Image enhancement using imagefusion techniques [J]. International Journal of AdvancedResearch in Computer Science and SoftwareEngineering, 2014, 4(9): 413-416.
[8]	HENNINGS-YEOMANS P H, VIJAYA KUMAR BV K, BAKER S. Robust low-resolution face identificationand verification using high-resolution features[C]//2009 16th IEEE International Conference on ImageProcessing (ICIP). Piscataway, USA: IEEE, 2009:33-36.
[9]	FREEMAN W T, PASZTOR E C, CARMICHAEL OT. Learning low-level vision [J]. International Journalof Computer Vision, 2000, 40(1): 25-47.
[10]	YANG J C, WRIGHT J, HUANG T S, et al. Imagesuper-resolution via sparse representation [J]. IEEETransactions on Image Processing, 2010, 19(11): 2861-2873.
[11]	HUANG J B, SINGH A, AHUJA N. Single imagesuper-resolution from transformed self-exemplars[C]//2015 IEEE Conference on Computer Vision andPattern Recognition (CVPR). Piscataway, USA: IEEE,2015: 5197-5206.
[12]	LEE S L, TSENG C C. Color image enhancementusing histogram equalization method without changinghue and saturation [C]//2017 IEEE InternationalConference on Consumer Electronics (ICCE). Piscataway,USA: IEEE, 2017: 305-306.
[13]	TIMOFTE R, DE SMET V, VAN GOOL L. Anchoredneighborhood regression for fast example-based superresolution[C]//2013 IEEE International Conferenceon Computer Vision (ICCV ). Piscataway, USA: IEEE,2013: 1920-1927.
[14]	JIANG J J, HU R M, WANG Z Y, et al. Facesuper-resolution via multilayer locality-constrained iterativeneighbor embedding and intermediate dictionarylearning [J]. IEEE Transactions on Image Processing,2014, 23(10): 4220-4231.
[15]	LU JW, ZHOU X Z, TAN Y P, et al. Neighborhood repulsedmetric learning for kinship verification [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2014, 36(2): 331-345.
[16]	GUO D G, WEN L Y, YAN S C. Face authenticationwith makeup changes [J]. IEEE Transactions on Circuitsand Systems for Video Technology, 2014, 24(5):814-825.
[17]	FANG Y C, LUO J, LOU C S. Fusion of multidirectionalrotation invariant uniform LBP featuresfor face recognition [C]// Third International Symposiumon Intelligent Information Technology Applications.Piscataway, USA: IEEE, 2009: 332-335.