Abstract
The traditional gradient is calculated along y and x axes, and its main object is to obtain vertical and horizontal edges in local image patch. However, there exist a lot of oblique edges in image patch besides vertical and horizontal edges. In order to obtain these oblique edges, we introduce multiple oblique gradient operators. By performing the multiple oblique gradient operators, an image can be transformed into multiple gradient orientation images which display different spatial locality and orientation properties. Each class orientation images are normalized by “z-score” method over the corresponding orientation image set. Then, linear discriminant analysis is performed to extract the corresponding low-dimensional features, and the results are used to compute the corresponding distance scores. The different weighted coefficients are calculated for different orientation images based on training samples. A weighted score fusion method is used to combine different distance scores according to their respective salience. Experimental results show that our methods significantly outperform popular methods, and achieve state-of-the-art performance for difficult problems such as illumination and occlusion-robust face recognition.
Similar content being viewed by others
References
Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041
An G, Wu J, Ruan Q (2010) Improved gradientface used in face recognition under varying illumination. In 2010 I.E. 10th International Conference on Signal Processing (ICSP). pp.670– 673
Baudat G, Anouar F (2000) Generalized discriminant analysis using a kernel approach. Neural Comput 12:2385–2404
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720
Berker Logoglu K, Saracoglu A, Esen E (2010) Gender classification via gradientfaces. Lect Notes Electr Eng 62:245–251
Calignano F, Vezzetti E (2010) Soft tissue diagnosis in maxillofacial surgery: a preliminary study on three-dimensional face geometrical features-based analysis. Aesthet Plast Surg 34(2):200–211
Cevikalp H, Neamtu M, Wilkes M (2006) Discriminative common vector method with kernels. IEEE Trans Neural Netw 17(6):1550–1565
Chengjun L (2004) Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Trans Pattern Anal Mach Intell 26(5):572–581
Chengjun L, Wechsler H (2002) Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans Image Process 11(4):467–476
Chengjun L, Wechsler H (2003) Independent component analysis of Gabor features for face recognition. IEEE Trans Neural Netw 14(4):919–928
Elhamifar E and Vidal R (2011) Robust classification suing structured sparse representation. In Proc. IEEE Int Conf. Comput Vis Pattern Recognit. pp.1873-1879
Freeman WT, Adelson EH (1991) The design and use of steerable filters. IEEE Trans Pattern Anal Mach Intell 13(9):891–906
Georghiades AS, Belhumeur PN, Kriegman DJ (2001) From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans Pattern Anal Mach Intell 23(6):643–660
Goudelis G, Zafeiriou S, Tefas A, Pitas I (2007) Class-specific kernel-discriminant analysis for face verification. IEEE Trans Inf Forensic Secur 2(3):570–587
Goudelis G, Zafeiriou S, Pantic M (2012) Subspace learning from image gradient orientations. IEEE Trans Pattern Anal Mach Intell 34(12):2454–2466
Hanai Y, Nishimura J, Kuroda T (2009) Haar-like filtering for human activity recognition using 3D accelerometer. In 5th IEEE Signal Processing Education Workshop. pp. 675–678
Jain A, Nandakumar K, Ross A (2005) Score normalization in multimodal biometric systems. Pattern Recogn 38(12):2270–2285
Kittler J, Hatef M, Duin R, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20(3):226–239
Lee C-J, Chen T-Y, Sun J-D, Yang T-N (2010) Combining gradientfaces, principal component analysis, and fisher linear discriminant for face recognition. In Sixth International Conference on Networked Computing and Advanced Information Management (NCM). pp.622-625
Lee KC, Ho J, Kriegman DJ (2005) Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans Pattern Anal Mach Intell 27(5):684–698
Lei Y, Chen D, Yuan M, Li Q., Shi Z, (2009) 3D face recognition by surface classification image and PCA. ICMV ’09 2nd International Conference on Machine Vision. pp. 145–149
Leng L, Zhang J, Khurram KM et al (2010) Dynamic weighted discrimination power analysis: a novel approach for face and palmprint recognition in DCT domain. Int J Phys Sci 5(17):2543–2554
Leng L, Zhang J, Xu J, Khurram KM et al (2010) Dynamic weighted discrimination power analysis in DCT domain for face and palmprint recognition. In International Conference on Information and Communication Technology Convergence (ICTC) pp:467–471
Martinez AM and Benavente R (1998) The AR face database. CVC technical report
Phillips PJ, Moon H, Rauss PJ, Rizvi S (2000) The FERET evaluation methodology for face recognition algorithms. IEEE Trans Pattern Anal Mach Intell 22(10):1090–1104
Poh N, Chan CH, Kittler J, Marcel S et al (2010) An evaluation of video-to-video face verification. IEEE Trans Inf Forensic Secur 5(4):781–801
Schiele B, Crowley JL (2000) Recognition without correspondence using multidimensional receptive field histograms. Int J Comput Vis 36(1):31–52
Shin H (2006) 3D face recognition with geometrically localized surface shape indexes. In ICARCV ’06. 9th International Conference. pp. 1–6
Tan X and Triggs B (2007) Enhanced local texture feature sets for face recognition under difficult lighting conditions. In Proc. IEEE Int’l Workshop Analysis and Modeling of Faces and Gestures. pp.168-182
Timo A, Abdenour H and Matti H (2004) Face recognition with local binary patterns. In Proc. Eur Conf. Comput Vis. pp.469-481
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71–86
Vezzetti E, Calignano F, Moos S (2010) Computer-aided morphological analysis for maxillo-facial diagnostic: a preliminary study. J Plast Reconstr Aesthet Surg 63(2):218–226
Wang Y, Pan G, Wu Z, Wang Y (2006) Exploring face expression effects in 3D face recognition using partial ICP. In Asian Conference on Computer Vision. pp. 581–590
Wright J, Yang A, Ganesh A, Sastry S, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Yang J, Frangi AF, Yang J, Zhang D, Jin Z (2005) KPCA plus LDA: a complete kernel fisher discriminant framework for feature extraction and recognition. IEEE Trans Pattern Anal Mach Intell 27(2):230–244
Yang M, Zhang L, Yang J and Zhang D (2011) Robust sparse coding for face recognition. In Proc. IEEE Int Conf. Comput Vis Pattern Recognit. pp.625-632
Yang M, Zhang L, Yang J, Zhang D (2013) Regularized robust coding for face recognition. IEEE Trans Image Process 22(5):1753–1766
Zhang T, Tang YY, Fang B et al (2009) Face recognition under varying illumination using gradientfaces. IEEE Trans Image Process 18(11):2599–2606
Zhao W, Chellappa R, Phillips PJ, Rosenfeld A (2003) Face recognition: a literature survey. ACM Comput Surv 34(4):399–485
Acknowledgments
The authors would like to thank the anonymous reviewers for their valuable comments and suggestions to improve the quality of this paper. This work was supported by the Special Project on the Integration of Industry, Education and Research of Guangdong Province of China Grant No. 2011B090400477; the Special Project on the Integration of Industry, Education and Research of Zhuhai of China Grant No. 2011A050101005,2012D0501990016; the Key Laboratory Key Technologies R & D Program of Zhuhai of China Grant No. 2012D0501990026.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, Z., Ding, L. & Wang, Y. Score level fusion method based on multiple oblique gradient operators for face recognition. Multimed Tools Appl 75, 819–837 (2016). https://doi.org/10.1007/s11042-014-2327-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-014-2327-1