A new biometric identity recognition system based on a combination of superior features in finger knuckle print images

Biometric methods are among the safest and most secure solutions for identity recognition and verification.One of the biometric features with sufficient uniqueness for identity recognition is the finger knuckle print (FKP). Thispaper presents a new method of identity recognition and verification based on FKP features, where feature extractionis combined with an entropy-based pattern histogram and a set of statistical texture features. The genetic algorithm(GA) is then used to find the superior features among those extracted. After extracting superior features, a supportvector machine-based feedback scheme is used to improve the performance of the biometric system. Two datasets calledPoly-U FKP and FKP are used for performance evaluation. The proposed method managed to achieve 94.91% and98.5% recognition rates on the Poly-U FKP and FKP datasets and outperformed all of the existing methods in thisrespect. These results demonstrate the potential of this method as a simple yet effective solution for FKP-based identityrecognition.

PDF

___

[1] Swati MR, Ravishankar M. Finger knuckle print recognition based on Gabor feature and KPCA+LDA. In: International Conference on Emerging Trends in Communication, Control, Signal Processing and Computing Applications; Bangalore, India; 2014. pp. 1-5.
[2] Galbally J, Marcel S, Fierrez J. Image quality assessment for fake biometric detection: application to iris, fingerprint and face recognition. IEEE Transactions on Image Processing 2014; 23: 710-724.
[3] Seetharaman K, Ragupathy R. Iris recognition for personal identification system. Procedia Engineering 2016; 38: 1531-1546.
[4] Grabowsk K, Napieralski A. Hardware architecture optimized for iris recognition. IEEE Transactions on Circuits and Systems for Video Technology 2011; 9: 1293-1303.
[5] Dey S, Samanta D. Iris data indexing method using Gabor energy features. IEEE Transactions on Information Forensics and Security 2012; 7: 1192-1203.
[6] Abramoff MD, Garvin MK, Sonka M. Retinal imaging and image analysis. IEEE Reviews in Biomed Engineering 2010; 3: 169-208.
[7] Kose C, Bas CI. A personal identification system using retinal vasculature in retinal fundus image. Expert Systems with Applications 2011; 38: 13670-13681.
[8] Radha R, Lakshman B. Identification of retinal image features using bitplane separation and mathematical morphology. In: World Congress on Computing and Communication Technologies; Trichirappalli, India; 2014. pp. 120-123.
[9] Bustard JD, Nixon MS. Toward unconstrained ear recognition from two dimensional images. IEEE Transactions on System, Man, and Cybernetics 2010; 40: 486-494.
[10] Kalluri HK. Palm print identification and verification with minimal number of features. Biometrics 2018; 10: 16-28.
[11] Parivazhagan A, Therese A. Face detection cum recognition system using novel techniques for human authentication. Biometrics 2018; 10: 315-333.
[12] Gao G, Yang J, Qian J, Zhang L. Integration of multiple orientation and texture information for finger-knuckle-print verification. Neurocomputing 2014; 135: 180-191.
[13] Zhang L, Zhang D, Guo Z. Phase congruency induced local features for finger-knuckle-print recognition. Pattern Recognition 2012; 45: 2522-2531.
[14] Woodard DL, Flynn PJ. Finger surface as a biometric identifier. Computer Vision and Image Understanding 2005; 100: 357-384.
[15] Ferrer MA, Travieso CM, Alonso JB. Using hand knuckle texture for biometric identification. In: 39th Annual International Carnahan Conference on Security Technology; Las Palmas, Spain; 2006. pp. 1-5.
[16] Ravikanth C, Kumar A. Biometric authentification using finger back surface. In: IEEE Conference on Computer Vision and Pattern Recognition; Minneapolis, MN, USA; 2007. pp. 1-6.
[17] Zhao R, Li K, Liu M, Sun X. A novel approach of personal identification based on single knuckle print image. In: Asia-Pacific Conference on Information Processing; Shenzhan, China; 2009. pp. 218-221.
[18] Shariatmadar ZS, Faez K. A novel approach for finger knuckle print recognition based on Gabor feature fusion. In: 4th International Congress on Image and Signal Processing; Shanghai, China; 2011. pp. 1480-1484.
[19] Morales A, Travieso CM, Ferrer MA, Alonso JB. Improved finger knuckle print authentication based on orientation enhancement. Electronic Letters 2011; 47: 380-381.
[20] Nigam A, Gupta P. Designing an accurate hand biometric based authentication system fusing finger knuckle print and palmprint. Neurocomputing 2015; 151: 1120-1132.
[21] Ozkaya N, Kurat N. Discriminative common vector based finger knuckle recognition. Visual Communication and Image Representation 2014; 25: 1647-1675.
[22] Grover J, Hanmandlu M. Hybrid fusion of score level and adaptive fuzzy decision level fusions for the finger-knuckleprint based authentication. Applied Soft Computing 2015; 31: 1-13.
[23] Qayyum A, Muhammad SM, Awais M, Majid M. Medical image retrieval using deep convolutional neural network. Neurocomputing 2017; 266: 8-20.
[24] Zhang H, Xue J, Dana K. DeepTEN: texture encoding network. Computer Vision and Pattern Recognition 2017; 1: 14-26.
[25] Pan Z, Li Z, Fan H, Wu X. Feature based local binary pattern for rotation invariant texture classification. Expert Systems with Applications 2017; 88: 238-248.
[26] Silva L, Duque J, Felipe J, Murta L. Two dimensional multiscale entropy analysis: Application to image texture evaluation. Signal Processing 2018; 147: 224-232.
[27] Fathi A, Nagh-Nilchi A. General rotation-invariant local binary patterns operator with application to blood vessel detection in retinal images. Pattern Analysis and Application 2014; 17: 69-81.
[28] Antic A, Popovic B, Krstanovic L, Obradovic R, Milosevic M. Novel texture based descriptors for tool wear condition monitoring. Mechanical Systems and Signal Processing 2018; 98: 1-15.
[29] Sawicki D, Miziolek W. Human colour skin detection in CMYK colour space. IET Image Processing 2015; 9: 751-757.
[30] Zhi H, Liu S. Face recognition based on genetic algorithm. Visual Communication and Image Representation 2019; 58: 495-502.
[31] Back T, Fogel DB, Michalewicz Z. Handbook of Evolutionary Computation. Bristol, UK: Institute of Physics, 1997. pp. 1-6.
[32] De P, Ghoshal D. Recognition of non-circular iris pattern of the goat by structural, statistical and Fourier descriptors. In: 12th International Multi-Conference on Information Processing; Bangalore, India; 2016. pp. 845-849.
[33] Harfiane A, Palaniappan K, Seetharaman G. Joint adaptive median binary patterns for texture classification. Pattern Recognition 2015; 48: 2609-2620.
[34] Kylberg G, Sintorn I. Evaluation of noise robustness for local binary pattern descriptors in texture classification. Image and Video Processing 2013; 17: 1-20.
[35] El-Alfy ES, Binsaadoon AG. Silhouette based gender recognition in smart environments using fuzzy local binary patterns and support vector machines. In: 8th International Conference on Ambient Systems, Networks and Technologies; Madeira, Portugal; 2017. pp. 164-171.
[36] Jung HG. Analysis of reduced-set construction using image reconstruction from a HOG feature vector. IET Computing Vision 2017; 11: 725-732.
[37] Joo HB, Jeon JW. Feature-point extraction based on an improved SIFT algorithm. In: 17th International Conference on Control, Automation and Systems; Jeju, South Korea; 2017. pp. 1-5.
[38] Busch A, Boles WW. Texture classification using multiple wavelet analysis. In: Digital Image Computing Techniques and Applications; Melbourne, Australia; 2002. pp. 1-5.
[39] Chakraborty S, Singh SK, Chakraborty P. Local quadruple pattern: a local descriptor for facial image recognition and retrieval. Computer and Electrical Engineering 2017; 62: 92-104.
[40] Abdullah MFA, Sayeed MS, Muthu KS, Bashier HK, Azman A et al. Face recognition with Symmetric local graph structure (SLGS). Expert Systems with Applications 2014; 41: 6131-6137.