Scale invariant and fixed-length feature extraction by integrating discrete cosine transform and autoregressive signal modeling for palmprint identification

Recently, the need for automatic identification has caused researchers to focus on biometric identification methods. Palmprint-based biometric identification has several advantages such as user friendliness, low-cost capturing devices, and robustness. In this paper, a method that integrates the discrete cosine transform (DCT) and an autoregressive (AR) signal modeling is proposed for biometric identification. The method provides scale invariance and produces a fixed-length feature vector. In particular, the Burg algorithm is used for the determination of the AR parameters used as a feature vector. Experimental results demonstrate that a small number of the AR parameters that are modeling the DCT coefficients of a palmprint are sufficient to constitute a practically applicable identification system achieving a correct recognition rate of 99.79%. The accuracy of the proposed approach is not overly dependent on the number of training samples, another advantage of the method.

PDF

___

[1] Kong A, Zhang D, Kamel M. A survey of palmprint recognition. Pattern Recogn 2009; 42: 1408-1418.
[2] Badrinath G, Gupta P. Stockwell transform based palmprint recognition. Appl Soft Comput 2011; 11: 4267-4281.
[3] Connie T, Jin ATB, Ong MGK, Ling DNC. An automated palmprint recognition system. Image Vision Comput 2005; 23: 501-515.
[4] Zhang D, Kong WK, You J, Wong M. Online palmprint identification. IEEE T Pattern Anal 2003; 25: 1041-1050.
[5] Zhang D, Guo Z, Lu G, Zhang L, Zuo W. An online system of multispectral palmprint verification. IEEE T Instrum Meas 2010; 59: 480-490.
[6] Ekinci M, Aykut M, Palmprint recognition by applying wavelet subband representation and kernel PCA. In: 5th International Conference on Machine Learning and Data Mining in Pattern Recognition; 1820 July 2007; Leipzig, Germany. Berlin, Germany: Springer. pp. 628-642.
[7] Jia W, Huang DS, Zhang D. Palmprint verification based on robust line orientation code. Pattern Recogn 2008; 41: 1504-1513.
[8] Wu X, Zhang D, Wang K. Palm line extraction and matching for personal authentication. IEEE T Syst Man Cy A 2006; 36: 978-987.
[9] Tao J, Jiang W, Gao Z, Chen S, Wang C. Palmprint recognition based on improved 2DPCA. Lect Notes Artif Int 2006; 4088: 455-462.
[10] Lu G, Zhang D, Wang K. Palmprint recognition using eigenpalms features. Pattern Recogn Lett 2003; 24: 1463-1467.
[11] Wu X, Zhang D, Wang K. Fisherpalms based palmprint recognition. Pattern Recogn Lett 2003; 24: 2829-2838.
[12] Pan X, Ruan QQ. Palmprint recognition using Gabor based local invariant features. Neurocomputing 2009; 72: 2040-2045.
[13] Li W, Zhang D, Xu Z. Palmprint identification by Fourier transform. Int J Pattern Recogn 2002; 16: 417-432.
[14] Jing XY, Zhang D. A face and palmprint recognition approach based on discriminant DCT feature extraction. IEEE T Syst Man Cy B 2004; 34: 2405-2415.
[15] Tiwari K, Arya DK, Badrinath G, Gupta P. Designing palmprint based recognition system using local structure tensor and force field transformation for human identification. Neurocomputing 2013; 116: 222-230.
[16] Sumathi S, Rani Hemamalini R. Person identification using palm print features with an efficient method of DWT. In: International Conference on Global Trends in Information Systems and Software Applications; 2012. Berlin, Germany: Springer. pp. 337-346.
[17] Mansoor AB, Masood H, Mumtaz M, Khan SA. A feature level multimodal approach for palmprint identification using directional subband energies. J Netw Comput Appl 2011; 34: 159-171.
[18] Dabbaghchian S, Ghaemmaghami MP, Aghagolzadeh A. Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology. Pattern Recogn 2010; 43: 1431-1440.
[19] Kumar A, Zhang D. Personal recognition using hand shape and texture. IEEE T Image Process 2006; 15: 2454-2461.
[20] Qing C, Jiang J. An EDBoost algorithm towards robust face recognition in JPEG compressed domain. Image Vision Comput 2010; 28: 1659-1670.
[21] Kishore KM, Addanki PR. An evaluation of palm print recognition techniques using DCT, Haar transform and DCT wavelets and their performance with fractional coefficients. International Journal of Computer Applications 2011; 32: 31-38.
[22] Lawhern V, Hairston WD, McDowell K, Westerfield M, Robbins K. Detection and classification of subject generated artifacts in EEG signals using autoregressive models. J Neurosci Meth 2012; 208: 181-189.
[23] Weiss J, Bernardara P, Andreewsky M, Benoit M. Seasonal autoregressive modeling of a skew storm surge series. Ocean Model 2012; 47: 41-54.
[24] Ergen B, Tatar Y, Gulcur HO. Timefrequency analysis of phonocardiogram signals using wavelet transform: a comparative study. Comput Method Biomec 2012; 15: 371-381.
[25] Ergen B. Texture analysis and classification using autoregressive signal modeling method. In: In: 1st Taibah University International Conference on Computing and Information Technology; 2012. pp. 107-110.
[26] Cho NI. Fast algorithm and implementation of 2D discrete cosine transform. IEEE T Circuits Syst 1991; 38: 297-305.
[27] Acharya UR, Sankaranarayanan M, Nayak J, Xiang C, Tamura T. Automatic identification of cardiac health using modeling techniques: a comparative study. Inform Sciences 2008; 178: 4571-4582.
[28] Mohamed SS, Salama MMA. Prostate cancer spectral multifeature analysis using TRUS images. IEEE T Med Imaging 2008; 27: 548-556.
[29] Proakis JG. Digital Signal Processing: Principles, Algorithms, and Applications. 4th ed. New Delhi, India: Pearson Education India, 2007.
[30] Subasi A, Er¸celebi E, Alkan A, Koklukaya E. Comparison of subspace based methods with AR parametric methods in epileptic seizure detection. Comput Biol Med 2006; 36: 195-208.
[31] Childers DG. Modern Spectrum Analysis. New York, NY, USA: IEEE Computer Society Press, 1978.
[32] Faust O, Acharya RU, Allen AR, Lin CM. Analysis of EEG signals during epileptic and alcoholic states using AR modeling techniques. IRBM 2008; 29: 44-52.
[33] Ubeylı ED, G¨uler ¨ ˙I. Comparison of eigenvector methods with classical and model-based methods in analysis of internal carotid arterial Doppler signals. Comput Biol Med 2003; 33: 473-493.
[34] Bos R, De Waele S, Broersen PMT. Autoregressive spectral estimation by application of the Burg algorithm to irregularly sampled data. IEEE T Instrum Meas 2002; 51: 1289-1294.
[35] Marple L. A new autoregressive spectrum analysis algorithm. IEEE T Acoust Speech 1980; 28: 441-454.
[36] Zhong L, Jinsha Y, Hong Y, Ke Z. Wireless communications, networking and mobile computing. In: WiCOM 2008 4th International Conference; 2008. pp. 1-4.
[37] Vadivel A, Majumdar A, Sural S. Performance comparison of distance metrics in content-based image retrieval applications. In: Proceedings of the International Conference on Information Technology; 2003; Bhubaneswar, India. pp. 159-164.
[38] Zhang D. PolyU Palmprint Database. Hong Kong: Biometric Research Centre, Hong Kong Polytechnic University, 2006.
[39] Kong WK, Zhang D, Li W. Palmprint feature extraction using 2D Gabor filters. Pattern Recogn 2003; 36: 2339- 2347.
[40] Pan X, Ruan Q. Palmprint recognition using Gabor feature based (2D)2PCA. Neurocomputing 2008; 71: 3032-3036.
[41] Lu J, Tan YP. Improved discriminant locality preserving projections for face and palmprint recognition. Neurocomputing 2011; 74: 3760-3767.