SIFT Based Vein Recognition Models : Analysis and Improvement

Scale-Invariant Feature Transform (SIFT) is being investigated more and more to realize a less-constrained hand vein recognition system. Contrast enhancement (CE), compensating for deficient dynamic range aspects, is a must for SIFT based framework to improve the performance.However, evidence of negative influence on SIFTmatching brought byCE is analysed by our experiments. We bring evidence that the number of extracted keypoints resulting by gradient based detectors increases greatly with different CE methods, while on the other hand the matching result of extracted invariant descriptors is negatively influenced in terms of Precision-Recall (PR) and Equal Error Rate (EER). Rigorous experiments with state-of-the-art and other CE adopted in published SIFT based hand vein recognition system demonstrate the influence. What is more, an improved SIFT model by importing the kernel of RootSIFT and Mirror Match Strategy into a unified framework is proposed to make use of the positive keypoints change and make up for the negative influence brought by CE.

[1]  Sang Min Yoon,et al.  Illumination Normalization for SIFT Based Finger Vein Authentication , 2012, ISVC.

[2]  H. N. Hazlyna,et al.  Image Enhancement Techniques Using Local, Global, Bright, Dark and Partial Contrast Stretching For Acute Leukemia Images , 2009 .

[3]  Hee Chan Kim,et al.  Finger vein extraction using gradient normalization and principal curvature , 2009, Electronic Imaging.

[4]  Christophe Rosenberger,et al.  Palm Vein Verification System Based on SIFT Matching , 2009, ICB.

[5]  Liming Chen,et al.  Hand-Dorsa Vein Recognition by Matching Local Features of Multisource Keypoints , 2015, IEEE Transactions on Cybernetics.

[6]  R. Kabacinski,et al.  Vein pattern database and benchmark results , 2011 .

[7]  Guoqing Wang,et al.  Hand Vein Recognition Based on Improved Template Matching , 2014 .

[8]  Stefan Winkler,et al.  Mirror Match: Reliable Feature Point Matching without Geometric Constraints , 2013, 2013 2nd IAPR Asian Conference on Pattern Recognition.

[9]  S. Pizer,et al.  An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement. , 1988, IEEE transactions on medical imaging.

[10]  Xiaohua Qian,et al.  Finger-Vein Recognition Based on the Score Level Moment Invariants Fusion , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[11]  Yang Liu,et al.  Contact-Free Palm-Vein Recognition Based on Local Invariant Features , 2014, PloS one.

[12]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[13]  Jen-Chun Lee,et al.  Palm vein recognition using adaptive Gabor filter , 2012, Expert Syst. Appl..

[14]  Ju Cheng Yang,et al.  Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex , 2015, Sensors.

[15]  Boonchana Purahong,et al.  Dorsal Hand Vein Image Enhancement for Improve Recognition Rate Based on SIFT Keypoint Matching , 2013 .

[16]  Dinu Coltuc,et al.  Contrast enhancement influences the detection of gradient based local invariant features and the matching of their descriptors , 2015, J. Vis. Commun. Image Represent..

[17]  Naoto Miura,et al.  Extraction of Finger-Vein Patterns Using Maximum Curvature Points in Image Profiles , 2007, MVA.

[18]  Liang Tao,et al.  Novel Algorithm for Hand Vein Recognition Based on Retinex Method and SIFT Feature Analysis , 2011 .

[19]  Qiuxia Wu,et al.  Palm vein recognition based on multi-sampling and feature-level fusion , 2015, Neurocomputing.

[20]  E H Land,et al.  An alternative technique for the computation of the designator in the retinex theory of color vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[21]  Fei Zhou,et al.  Comparative competitive coding for personal identification by using finger vein and finger dorsal texture fusion , 2014, Inf. Sci..

[22]  X. Xu,et al.  Evaluating Gabor preprocessing for SIFT-based ocular recognition , 2011, ACM-SE '11.

[23]  Weon-Geun Oh,et al.  An analysis of the effect of different image preprocessing techniques on the performance of SURF: Speeded Up Robust Features , 2011, 2011 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV).

[24]  Fabio A. González,et al.  Visual pattern mining in histology image collections using bag of features , 2011, Artif. Intell. Medicine.

[25]  Xin Li,et al.  A New Approach to Hand Vein Image Enhancement , 2009, 2009 Second International Conference on Intelligent Computation Technology and Automation.

[26]  Andrew Zisserman,et al.  Three things everyone should know to improve object retrieval , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Hee Chan Kim,et al.  A finger-vein verification system using mean curvature , 2011, Pattern Recognit. Lett..

[28]  Fazal A. Talukdar,et al.  Impact of image preprocessing on face recognition: A comparative analysis , 2014, 2014 International Conference on Communication and Signal Processing.

[29]  Li Xueyan,et al.  Vein Pattern Recognitions by Moment Invariants , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[30]  Kang Ryoung Park,et al.  Finger vein recognition using minutia‐based alignment and local binary pattern‐based feature extraction , 2009, Int. J. Imaging Syst. Technol..

[31]  D.H. Rao,et al.  A Survey on Image Enhancement Techniques: Classical Spatial Filter, Neural Network, Cellular Neural Network, and Fuzzy Filter , 2006, 2006 IEEE International Conference on Industrial Technology.

[32]  Wenxiong Kang,et al.  Palm Vein Recognition Based on Three Local Invariant Feature Extraction Algorithms , 2011, CCBR.

[33]  P. Neelamegam,et al.  Enhancement of Vein Patterns in Hand Image for Biometric and Biomedical Application using Various Image Enhancement Techniques , 2012 .

[34]  Rajeev Srivastava,et al.  PDE Based Unsharp Masking, Crispening and High Boost Filtering of Digital Images , 2009, IC3.

[35]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[36]  Robert A. Hummel,et al.  Image Enhancement by Histogram transformation , 1975 .

[37]  Xiubao Sui,et al.  Range Limited Bi-Histogram Equalization for image contrast enhancement , 2013 .

[38]  Jen-Chun Lee,et al.  A novel biometric system based on palm vein image , 2012, Pattern Recognit. Lett..