Touchless Fingerprint Recognization System

Transcription

1 e-issn Volume 2 Issue 4, April 2016 pp Scientific Journal Impact Factor : Touchless Fingerprint Recognization System Biju V. G 1., Anu S Nair 2, Albin Joseph 3, Bhavani Petchiammal 4, Jouhara Mahar 5, Manchula Devi 6 1 Associate Professor, College of Engineering Munnar 2,3,4,5,6 Department of ECE, College of Engineering Munnar Abstract In this paper we present a system which is a reliable alternative to conventional touch based finger print recognization system. The conventional system uses live acquisition techniques in which it suffers from many problems as they are less hygiene, maintanence,latent fingerprint. To overcome this difficulty we propose a new method that captures image of fingerprint using digital camera.the touchless fingerprint recognization system can be divided into three main modules: Preprocessing,Feature extraction and matching. Here we use several Preprocessing steps on binary image to enhance the quality of image followed by minutea, removal of false minutea followed by matching. Final step is minutea matching. The challenging Problem that acquire while developing the touchless system is low contrast between the ridge and valley pattern on fingerprint image, motion blurriness and defocus due to the less depth of field of digital camera, so in order to reduce this drawback we concentrate more on preprocessing so all the errors are removed. Keywords Fingerprint, Ridges, Furrows, Minutia, Feature Extraction, image segmentation, thining I. INTRODUCTION Fingerprint recognization system have been widely used for user authentication due to their reliable performance and usability compared to other biometric system. Various kinds of fingerprint image acquisition sensors including optical,solid state, thermal, ultrasound etc have been utilized for forensic and commercial application. Example e-commerce, access control, issuing national id cards and e-passports etc. Because these system are touch based user must place his fingers on platen surface and apply enough pressure to capture the image. This may damage the image that causes degradation of images due to skin deformation and skin condition changes. So a new method called touchless fingerprint technology is proposed to overcome this difficulty. II. EXISTING SYSTEM In touch based Finger print recognition system there exist deformation in captured image due to various factors. In figures 2(a and b) show two different images from same figure. Due to deformation the relative positions of minutea sets of two images are different. In figures 2 (c and d) there exist change in minutea type due to non uniform pressure of the finger. In figure 2(e) the ridge valley pattern is affected by various skin condition. In figure 2(f),show that a latent fingerprint remaining on the sensor surface can degrade the enhancement result of a newly captured image, Therefore representation of same finger print can vary at each acquisition resulting in the inevitable degradation of authentication performance, which causes forgeries in touch based sensor All rights Reserved 501

2 Figure 1: Distorted images acquired from a touch based sensor III. PROPOSED METHOD To solve the problems concerning touch based system, several advances in fingerprint sensing technology have been initiated. Capturing multispectral fingerprint imaging (MRI) techniques is introduced to acquire better quality images from dry or wet finger and optical sensors with high resolution (over 1000dpi) have been proposed to observe various fingerprint features including sweat pore, ridges, scar and so on. However, this system also has some disadvantages as non uniform,inconsistent and irreproducible contacts. To avoid this problem, a touchless fingerprint recognization system has been proposed that does not require a contact between a sensor and figure. Also it can capture fingerprint image consistently because it is not affected by different skin conditions or latent finger print. This device consists of Single camera and LED based illuminators that considers minutea and illumination as important factors. Figure 2:Block diagram of the touchless fingerprint system A Fingerprint id believed to be unique to each person, even an identical twins have different fingerprint. The pattern is quite stable through our life time, in case of a cut the same pattern will grow back and these features depends on the nerve growth of the skin. This factor is determined by genetic factors and environmental factors such as nutrients, oxygen level, blood flow etc Impression of the fingerprint may be left on the surface by natural secretion of sweat from eccrine glands that are present in friction ridge skin, or they may be made by ink or other substances transferred from the peak of friction ridges on the skin. Fingerprints are considered to be an important proof in legal courts as evidence. Therefore Fingerprints are worldwide used for criminal investigation. On touch based system 90% of images captured are due to skin condition, sensor noise, deformation a significant of images are of poor quality.so we propose a Touchless finger print recognisation system for future All rights Reserved 502

3 Figure. 3: Minutiae Extraction 3.1 STAGES OF PROCESSING Raw data of fingerprint image obtained is in the RGB format. The fingerprint image in the RGB format is then changed into gray scale image so that image processing can be executed on the image. Matlab built-in function rgb2gray is used to convert RGB image to gray scale image. Sometimes, the image obtained does not have good quality and thus the purpose of enhancement is to process the image obtained so as to make it clearer by improving perception or interpretability and hence the accuracy of matching will be increased. By enhancing the image, the quality of image can be upgraded and thus the contrast between ridges and valleys can be increased. Enhancement for image can make the following process easier. This process is very important in keeping the performance of the fingerprint analysis at high accuracy. Image binarization is one of the image preprocessing stages with the purpose of converting a gray scale image into a binary image. Gray scale image has 256 gray levels (0-255) while a binary image consists of 0-1 (black and white) where 0 is for black and 1 is for white. Binarization is an important process as binary image is needed for the thinning process instead of gray scale image. Binary image is easy to generate, store and manipulate as the pixel is only a single bit as compared to gray scale image. Threshold value for binarization process can be obtained from the average gray value. However, proper threshold value in separating black pixel and white pixel is hard to determine. Some gray values may represent ridges at certain area but it may turn out to be representing furrow at other area. After image enhancement the next step is fingerprint image segmentation. In general, only a Region of Interest (ROI) is useful to be recognized for each fingerprint image. The image area without effective ridges (black) and Furrows (white) is first eliminated since it only holds background information. Then the bound of the remaining effective area is sketched out since the minutiae in the bound region are confusing with those spurious minutiae that are generated when the ridges are out of the sensor. To extract the region of interest, a method used is by ROI extraction by Morphological methods. The last step after feature extraction is matching minutia. Algorithms that extract important and efficient minutiae, will improve the performance of the fingerprint matching techniques. The features extracted of the input image are compared to one or more template that was previously stored in the system database. Therefore the system returns either a degree of similarity in case of identification or a binary decision in case of verification. Minutiae based technique is most common techniques in fingerprint matching. In Minutiae based techniques, first systems extract the All rights Reserved 503

4 in both images then the decision is based on the correspondence of the two sets of minutiae locations. Minutiae-based technique is the most widely used technique in fingerprint matching. IV. RESULT AND DISCUSSION: Figure 4:Input Image Figure 5:Skin colour detection Figure 6:Gray scale image Figure 7:Black and white image Figure 8:Mask Image Figure 9:Minutea Detection Since all the Problems concerning the touch based finger print image technology is eliminated in this technology it is considered to be prior than the earlier method. In this technique it undergoes several steps such as normalization that reduces the noise in the input image so that a photo with poor quality can be converted to a good quality image. Next it undergoes image segmentation followed by skin colour detection, adaptive thresholding and morphological process. Then it is followed by Feature extraction and finally it matches the image with database stored. In touch based system there is a chance that the fingerprint may get distorted or degraded due to many conditions or the user has to apply enough pressure so that the fingerprint may get distorted. This problem is eliminated in this proposed All rights Reserved 504

5 V. CONCLUSION This paper describes a novel touchless fingerprint sensing device which uses camera. The proposed paper is implemented in three stages; pre-processing, minutia extraction, and post processing. Like a touch based system we can use this system in forensic applications like criminal investigations, terrorist identification and other security issues. Fingerprint recognition is considered as safe and convenient personal identification system. Eventually, fingerprint recognition will be used to secure the safety and reliability of a variety of businesses in the industrial sector, including the personal devices and financial industry. Our method used minutiae as the initial correspondences. Therefore, if matched minutiae are wrongly detected, the results can be worse due to the misalignment of ridge and valley structures. Therefore, in our future work, we will develop a touchless fingerprint enhancement technique for stable feature REFERENCE [1] Lin Hong, Student Member, IEEE, Yifei Wan, and Anil Jain Fingerprint Image Enhancement: Algorithm and Performance Evaluation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 8, August 1998 [2] Burges, C.J.C., A tutorial on Support vector Machine for Pattern Recognition, Knowledge Discovery and Data Mining, vol.2, no.2, [3] B.Y. Hiew, Andrew B.J. Teoh, Member, IEEE and Y.H.Pang, Digital Camera based Fingerprint Recognition IEEE International Conference on Telecommunications and Malaysia International Conference on Communications, 2007, Penang, Malaysia. [4] Lin Hong, Student Member, IEEE, Yifei Wan, and Anil Jain Fingerprint Image Enhancement: Algorithm and Performance Evaluation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 8, August [5] Kenneth Nilsson and Josef Bigun, Localization of corresponding points in fingerprints by complex filtering,pattern Recognition Letters, vol. 24, pp , [6] S. Chikkerur, A. Cartwright, and V. Govindaraju, Fingerprint Image Enhancement Using STFT Analysis, International Conference on Advances in Pattern Recognition, United Kingdom, Perception, 33 (2004). Digital Image Processing With MATLAB By Gonzalez, 3rd Edition [7] S. Chikkerur, A. Cartwright, and V. Govindaraju, "Fingerprint Image Enhancement Using STFT Analysis", International Conference on Advances in Pattern Recognition, United Kingdom, 2005 [8] T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino, Impact of artificial gummy fingers on fingerprint systems, in Proc. SPIE, Optical Security and Counterfeit Deterrence Techniques IV, 2002, vol. 4677, pp [9] L. C. Jain, U. Halici, I. Hayashi, S. B. Lee, and S. Tsutsui, Intelligent biometric techniques in fingerprint and face Recognition, The CRC All rights Reserved 505