Palmprint Recognition: A Review

Transcription

1 Palmprint Recognition: A Review Yogesh Dhanotiya M. Tech. Scholar Computer Sc. & Engg. Dept. IES, IPS Academy, Indore (India) ydyoooogi@gmail.com Neeraj Shrivastava Associate Professor Computer Sc. & Engg. Dept. IES, IPS Academy, Indore (India) neerajshrivastava@ipsacademy.org Arvind Upadhyay Associate Professor Computer Sc. & Engg. Dept. IES, IPS Academy, Indore (India) upadhyayarvind10@gmail.com Abstract Palmprint recognition being one of the important aspects of biometric technology is one of the most reliable and successful identification methods. Palmprint is an important complement and reliable biometric that can be used for identity verification because it is stable and unique for every individual. This paper reviews about the current research work on palmprint recognition techniques. Keywords 2D-DWT, CASIA, DWT, DCT, Euclidean Distance, LBP, LBPH, PCA. I. INTRODUCTION Palm print recognition inherently implements many of the same matching characteristics that have allowed fingerprint recognition to be one of the most well-known and best publicized biometrics. Both palm and finger biometrics are represented by the information presented in a friction ridge impression. This information combines ridge flow, ridge characteristics, and ridge structure of the raised portion of the epidermis. The data represented by these friction ridge impressions allows a determination that corresponding areas of friction ridge impressions either originated from the same source or could not have been made by the same source. Because fingerprints and palms have both uniqueness and permanence, they have been used for over a century as a trusted form of identification. However, palm recognition has been slower in becoming automated due to some restraints in computing capabilities and live-scan technologies. This paper provides a brief overview of the historical progress of and future implications for palm print biometric recognition. II. HISTORY OF PALMPRINT RECOGNITION In many instances throughout history, examination of handprints was the only method of distinguishing one illiterate person from another since they could not write their own names. Accordingly, the hand impressions of those who could not record a name but could press an inked hand onto the back of a contract became an acceptable form of identification. In 1858, Sir William Herschel, working for the Civil Service of India, recorded a handprint on the back of a contract for each worker to distinguish employees from others who might claim to be employees when payday arrived. This was the first recorded systematic capture of hand and finger images that were uniformly taken for identification purposes. The first known AFIS system built to support palm prints is believed to have been built by a Hungarian company. In late 1994, latent experts from the United States benchmarked the palm system and invited the Hungarian company to the 1995 International Association for Identification (IAI) conference. The palm and fingerprint identification technology embedded in the palm system was subsequently bought by a US company in In 2004, Connecticut, Rhode Island and California established statewide palm print databases that allowed law enforcement agencies in each state to submit unidentified latent palm prints to be searched against each other's database of known offenders. Australia currently houses the largest repository of palm prints in the world. The new Australian National Automated Fingerprint Identification System (NAFIS) includes 4.8 million palm prints. The new NAFIS complies with the ANSI/NIST international standard for fingerprint data exchange, making it easy for Australian police services to provide fingerprint records to overseas police forces such as Interpol or the FBI, when necessary. Over the past several years, most commercial companies that provide fingerprint capabilities have added the capability for storing and searching palm print records. While several state and local agencies within the US have implemented palm systems, a centralized national palm system has yet to be developed. Currently, the Federal Bureau of Investigation (FBI) Criminal Justice

2 Information Services (CJIS) Division houses the largest collection of criminal history information in the world. This information primarily utilizes fingerprints as the biometric allowing identification services to federal, state, and local users through the Integrated Automated Fingerprint Identification System (IAFIS). The Federal Government has allowed maturation time for the standards relating to palm data and live-scan capture equipment prior to adding this capability to the current services offered by the CJIS Division. The FBI Laboratory Division has evaluated several different commercial palm AFIS systems to gain a better understanding of the capabilities of various vendors. Additionally, state and local law enforcement have deployed systems to compare latent palm prints against their own palm print databases. It is a goal to leverage those experiences and apply them towards the development of a National Palm Print Search System. In April 2002, a Staff Paper on palm print technology and IAFIS palm print capabilities was submitted to the Identification Services (IS) Subcommittee, CJIS Advisory Policy Board (APB). The Joint Working Group then moved for strong endorsement of the planning, costing, and development of an integrated latent print capability for palms at the CJIS Division of the FBI. This should proceed as an effort along the same parallel lines that IAFIS was developed and integrate this into the CJIS technical capabilities. As a result of this endorsement and other changing business needs for law enforcement, the FBI announced the Next Generation IAFIS (NGI) initiative. A major component of the NGI initiative is the development of the requirements for and deployment of an integrated National Palm Print Service. Law enforcement agencies indicate that at least 30 percent of the prints lifted from crime scenes from knife hilts, gun grips, steering wheels, and window panes are of palms, not fingers. For this reason, capturing and scanning latent palm prints is becoming an area of increasing interest among the law enforcement community. The National Palm Print Service is being developed on the basis of improving law enforcement s ability to exchange a more complete set of biometric information, making additional identifications, quickly aiding in solving crimes that formerly may have not been possible, and improving the overall accuracy of identification through the IAFIS criminal history records. III. PALM-PRINT IDENTIFICATION Palmprint identification can be divided into two categories, on-line and offline. Figure 1 (a) and Figure 1 (b) show an on-line palmprint image and an offline palmprint image, respectively. Research on offline palmprint identification has been the main focus in the past few years. Due to the relative highresolution offline palmprint images (up to 500 dpi), some techniques applied to fingerprint images could be useful for offline palmprint identification, where lines, datum points and singular points can be extracted. For on-line palmprint authentication, the samples are directly obtained by a palmprint scanner [18]. Figure 2 (a) shows a palmprint image captured by palmprint scanner and Figure 2 (b) shows the outlook of the scanner device [18]. (a) (b) Figure 1: Examples of (a) on-line, with line definitions and (b) off-line palmprint images (a) (b) Figure 2: (a) Palmprint image captured by palmprint scanner and (b) palmprint scanner device Figure 3 shows the basic palmprint recognition system. Image Acquisition Preprocessing Feature Database Extraction Matcher Result Figure 3: Basic block diagram of palmprint recognition system Palmprint Image Acquisition The Palmprint image acquisition has two methods. The offline and online methods are used. In offline, the palm is painted with ink and put it on paper then it is scanned. This collection method is very slow, it is not suitable for real time applications. So usually online method is used.

3 Preprocessing The preprocessing is used to segment the centre for feature extraction and set up a coordinate system. Preprocessing consists of five steps, 1) binarize the images, 2) boundary extraction, 3) detecting the key points, 4) establish a coordination system and 5) extracting the central part. Feature Extraction Once the central part is segmented, features can be extracted for matching. The features defined possess the stable and unique properties of low intra-class difference and high interclass difference. These features are used to create a master template which is stored in the system database. Database It is used to store the features obtained from the feature extraction phase. Matching A distance measure is used to measure the similarity of two Palmprints. A matching score is obtained by matching the identification template against the master templates. If the score is less than a given threshold the user is authenticated. IV. LITERATURE REVIEW Jaswal et al. [1] presented a texture based palm print recognition method which employ 2D Gabor filter to extract texture information from the central part of hand and use subspace methods for dimension reduction. The test and training images are compared in terms of calculating Euclidean distance between them. Algorithm is tested on standard benchmark databases (CASIA and IIT Delhi). Sang et al. [2] proposed a robust, touchless, palmprint recognition system which is based on color palm-print images. This system uses skincolor thresholding and hand valley detection algorithm for extracting palmprint. Then, the local binary pattern (LBP) is applied to the palmprint in order to extract the palmprint features. Finally, chi square statistic is used for classification. Khalifa et al. [3] presented an authentication system based on the palmprint. This paper particularly interested in the feature extraction step. Three feature extraction techniques based on the discrete wavelet transform, the Gabor filters and the co-occurrence matrix are evaluated. The support vector machine is used for the classification step. Puranik et al. [4] proposed an innovative touch-less, web camera based palm print recognition system. It describes to use a low-resolution web camera to capture the user s hand at a distance for recognition. The user does not need to touch any device for their palm print to be acquired. This system consists of two parts: a novel device for online palmprint image acquisition and an efficient algorithm for fast palmprint recognition. Raut et al. [5] proposed a Biometric Palm print lines extraction using image processing morphological operation. This work discusses the significance; since both the palm print and hand shape images are proposed to extract from the single hand image acquired from a sensor. The basic statistical properties can be computed and are useful for biometric recognition of individual. It describes biometric recognition of individual by using basic statistical properties of palm print image. Seshikala et al. [6] carried out the feature extraction of palm print using multi scale wavelet edge detection. The performance is compared with conventional edge detection techniques like Sobel and Canny methods. The experiment is carried out on a poly-u database and from the analysis it is shown that the performance of multiscale edge detection using wavelet is much superior to that of Sobel and Canny for palm print feature extraction. Shashikala et al. [7] proposed a palmprint identification system based on DWT, DCT and QPCA (PIDDQ). Histogram equalization is used on palmprint to enhance contrast of an image. The DWT is applied on Histogram equalized image to generate LL, LH, HL and HH bands. The LL band is converted into DCT coefficients using DCT. QPCA is applied on DCT coefficients to generate features. The test and database palmprint features are compared using Euclidean Distance (ED). Kumar et al. [8] proposed a technique for palmprint recognition in context to biometric identification of a person. Palmprints are images of the inner portion of a person s palm and consist of a complex pattern of randomly oriented curves and lines. This random pattern can provide a unique identifier of a person if a mathematical model can be built to represent and compare it. In this paper the palmprint images are mapped to Eigen-space and a robust code signature is generated from different camera snapshots of the same palm to incorporate tonal and lighting variations. To enable real-time identification, the signature is represented by a low dimensional feature vector to reduce computational overheads. It is observed to produce high recognition accuracies which highlight reliability of the feature. Gayathri et al. [9] presented a palmprint based identification approach which uses the Gabor

4 wavelet to extract multiple features available on the palmprint, by employing a feature level fusion and classified using nearest neighbor approach. Here, the features are extracted using wavelet entropy consist of contrast, correlation, energy, and homogeneity. The features are fused at feature levels. Palmprint matching is then performed by using nearest neighbor classifier. Guo et al. [10] presented an approach for palmprint recognition from a single image per person based on local information. First, a palmprint image is partitioned into several smaller sub-images, then the feature vectors are extracted by five methods. They are statistics feature, Fourier transform, DCT transform, Gabor transform and local binary pattern (LBP). The feature vectors of all the sub-images are combined together to form the feature vector of the palmprint image. Finally the pattern classification can be implemented by the nearest neighbor classifier. To verify the effectiveness of this approach, an extensive experimental investigation is conducted using Poly U palmprint database. Kallibaddi et al. [11] attempt to improve the performance of hand-geometry based identification system by integrating palmprint features. Hand-geometry and palmprint features can be collected simultaneously from the same hand image. Fourteen different hand-geometry distances are extracted from the hand image. Texture information from palmprint is extracted using Symmelt-8 wavelet transform. Both hand-geometry and palmprint features are combined at feature level. The identification of the user is carried out using Euclidean distance classifier. Malik et al. [12] proposed a palmprint based biometric authentication method with improvement in accuracy, so as to make it a real time palmprint authentication system. Several edge detection methods, Directional operator, Wavelet transform, Fourier transform etc. are available to extract line feature from the palmprint. In this paper, Sobel Code operators, canny edge and Phase Congruency methods are applied to the palmprint image to extract palmprint features. The extracted Palmprint features are stored in Palmprint feature vector. The corresponding feature vectors are matched using sliding window with Hamming Distance similarity measurement method. In this paper, a Min Max Threshold Range (MMTR) method is described that helps in increasing overall system accuracy by reducing the False Acceptance Rate (FAR). The person authenticated by reference threshold is again verified by second level of authentication using MMTR method. Dai et al. [13] proposed a recognition algorithm for high-resolution palmprint. The main contributions of the proposed algorithm include: (1) Use of multiple features, namely minutiae, density, orientation and principal lines for palmprint recognition to significantly improve the matching performance of the conventional algorithm. (2) Design of a quality based and adaptive orientation field estimation algorithm, which performs better than the existing algorithm in case of regions with large number of creases. (3) Use of a novel fusion scheme for identification application which performs better than conventional fusion methods, e.g. weighted sum rule, SVMs or Neyman-Pearson rule. Besides, this paper describes the discriminative power of different feature combinations and find that density is very useful for palmprint recognition. Imtiaz et al. [14] implemented a multiresolution feature extraction algorithm for palmprint recognition based on two-dimensional discrete wavelet transform (2D-DWT), which efficiently exploits the local spatial variations in a palm-print image. The entire image is segmented into several small spatial modules and a palm-print recognition scheme is developed, which extracts histogrambased dominant wavelet features from each of these local modules. This not only drastically reduces the feature dimension but also results in a very high within-class compactness and between-class separability of the extracted features. Moreover, the improvement of the quality of the extracted features as a result of illumination adjustment has also been analyzed. A principal component analysis is performed to further reduce the feature dimension. Kumar et al. [15] investigated an approach for the personal recognition using rank level combination of multiple palmprint representations. There has been very little effort to study rank level fusion approaches for multi-biometrics combination and in particular for the palmprint identification. This paper proposes a nonlinear rank level fusion approach and present a comparative study of rank level fusion approaches which can be useful in combining multi-biometrics fusion. Wang et al. [16] improved the Local Binary Pattern Histogram (LBPH) approach and combine it with Dual-Tree Complex Wavelet Transform (DT- CWT) to propose a Dual-Tree Complex Wavelet Transform based Local Binary Pattern Weighted Histogram (DT-CWT based LBPWH) method for palmprint representation and recognition.

5 Edward et al. [17] described a simple and effective methodology for palmprint based identification system. The right hand image is captured using a digital camera without pegging or illumination arrangements. The captured image is aligned using identified key points in the hand and the palmprint region is selected for enhancement and resizing. Different feature extraction methods, namely Discrete Cosine Transform energy features, Wavelet Transform energy features and SobelCode are applied to the resized image to obtain feature vectors. The extracted feature vectors are matched using similarity measurement and feed forward back propagation neural network. Panigrahy et al. [18] presented an efficient approach to the palmprint preprocessing scheme. In real-time palmprint verification the input subject to the scanner for image acquisition may suffer rotational as well as translational variation. Because when the user puts his/her palm on the scanner, the angle and position of the palm may change. So, different images are acquired by the scanner according to the input each time. This paper presents a rotational- and translational-invariant scheme of palmprint image preprocessing, which generates low resolution palmprint images for personal authentication by which the above problem can be overcome while preprocessing the image before the feature extraction of the palmprint. Han et al. [19] proposed a palmprint recognition method by combining statistical texture descriptions of local image regions and their spatial relations. In this method, for each image block, a spatial enhanced histogram of gradient directions is used to represent discriminative texture features. Furthermore, similarity is measured between two palmprint images using a simple graph matching scheme, making use of structural information. Experimental results on two large palmprint databases demonstrate the effectiveness of this approach. Hernandez et al. [20] presented a biometric identification system based on palmprint local features. For this purpose, the error rate (ER) of 3 different preprocessing methods have compared. V. CONCLUSION It is believed that palm print is unique to individuals. They remain unchanged throughout at least a certain period during the adult life of an individual. Current system has many drawbacks in terms of recognition rate that they cannot recognize the palm print in the worst cases, and these drawbacks are directly depends upon the feature extraction technique used. For instance, iris based methods which are the most reliable, require more expensive acquisition systems than Palmprint systems. Face and voice characteristics are easier to acquire than Palmprints, but they are not so reliable. Overall, palmprint based systems are well balanced in terms of cost and performance. REFERENCE [1] Gaurav Jaswal, Ravinder Nath, Amit Kaul, Texture based Palm Print Recognition using 2-D Gabor Filter and Sub Space Approaches, IEEE, International Conference on Signal Processing, Computing and Control (ISPCC), pp , [2] Haifeng Sang, Yueshi Ma, Jing Huang, Robust Palmprint Recognition Base on Touch-Less Color Palmprint Images Acquired, Journal of Signal and Information Processing, PP , [3] Anouar Ben Khalifa, Lamia Rzouga, Najoua Essoukri BenAmara, Wavelet, Gabor Filters and Co-occurrence Matrix for Palmprint Verification, International Journal of Image, Graphics and Signal Processing (IJIGSP), ISSN: , Vol. 5, No. 8, June [4] Apurva Puranik, Rahul Patil, Varsha Patil, Milind Rane, Touch less, Camera Based Palm Print Recognition, International Journal of Applied Research and Studies (IJARS) ISSN: , Volume 2, Issue 4, April [5] Mr. Shriram D. Raut, Dr. Vikas T. Humbe, Biometric Palm Prints Feature Matching for Person Identification, International Journal of Modern Education and Computer Science (IJMECS), ISSN: , Vol. 4, No. 11, December [6] G. Seshikala, Dr. Umakanth Kulkarni, Dr. M. N. Giriprasad, Palm Print Feature Extraction Using Multi Scale Wavelet Edge Detection Method, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, ISSN: , Vol. 1, Issue 1, July [7] K. P. Shashikala, K. B. Raja, Palmprint Identification Based on DWT, DCT and QPCA, International Journal of Engineering and Advanced Technology (IJEAT) ISSN: , Volume-1, Issue-5, June [8] Ashutosh Kumar, Ranjan Parekh, Palmprint Recognition in Eigen-space, International Journal on Computer Science and Engineering (IJCSE), ISSN : , Vol. 4, No. 05, PP , May [9] R. Gayathri, P. Ramamoorthy, Multifeature Palmprint Recognitionusing Feature Level Fusion, International Journal of Engineering Research and Applications (IJERA), ISSN: , Vol. 2, Issue 2, PP , April [10] Jinyu Guo, Yuqin Liu, Weiqi Yuan, Palmprint Recognition Using Local Information From a Single Image Per Person, Journal of Computational Information Systems, ISSN: , Vol. 8, Issue 8, PP , April [11] Jayashree I. Kallibaddi, S.M. Hatture, Sadanand R. Inamdar, Hand Image Analysis for Personal Authentication, XI Biennial Conference of the International Biometric Society (Indian Region) on Computational Statistics and Bio-Sciences, March 2012.

6 [12] Jyoti Malik, G. Sainarayanan, Ratna Dahiya, Personal Authentication Using Palmprint With Sobel Code, Canny Edge And Phase Congruency Feature Extraction Method, ICTACT Journal on Image and Video Processing, ISSN: , Volume: 02, Issue: 03, February 2012, [13] Jifeng Dai, Jie Zhou, Multifeature-Based High- Resolution Palmprint Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Biometrics Compendium, ISSN: , Volume 33, Issue 5, PP , May [14] Hafiz Imtiaz, Shaikh Anowarul Fattah, A Waveletbased Feature Selection Scheme for Palm-print Recognition, International Journal of Modern Engineering Research (IJMER), ISSN: , Vol.1, Issue.2, PP , [15] Ajay Kumar, Sumit Shekhar, Palmprint Recognition using Rank Level Fusion, 17th IEEE International Conference on Image Processing (ICIP), ISSN: , PP , September [16] Yanxia Wang, Qiuqi Ruan, Dual-Tree Complex Wavelet Transform Based Local Binary Pattern Weighted Histogram Method for Palmprint Recognition, Computing and Informatics, Vol. 28, No. 3, PP , [17] Edward Wong Kie Yih, G. Sainarayanan, Ali Chekima, Palmprint Based Biometric System: A Comparative Study on Discrete Cosine Transform Energy, Wavelet Transform Energy and SobelCode Methods, International Journal of Biomedical Soft Computing and Human Sciences, Vol.14, No.1, pp.11-19, [18] Saroj Kumar Panigrahy, Debasish Jena, Sanjay Kumar Jena, An Efficient Palmprint Image Recognition System, Technical Journal of Synergy Institute of Engineering & Technology, Dhenkanal, Orissa, India Vol.-1, Issue- 1. PP , [19] Yufei Han, Tieniu Tan, Zhenan Sun, Palmprint Recognition Based on Directional Features and Graph Matching, Springer, Advances in Biometrics Lecture Notes in Computer Science Volume 4642, PP , [20] Jose Garcia-Hernandez, Roberto Paredes, Biometric Identification Using Palmprint Local Features, 3rd COST 275 Workshop, Biometrics on the Internet Fundamentals Advances and Applications, PP , 2005.