SLP Header

Retinal vascular Segmentation, classification and Verification using particle swarm optimization for biometric application

IJCSEC Front Page

Abstract
Biometric authentication plays an important role in this paper. Biometrics is measurable biological (anatomical and physiological) and behavioral characteristics that can be used for automated reorganization Among the features measured for physiological are face reorganization, finger prints, hand and finger geometry, iris, retinal, signature, vein pattern and voice reorganization. Behavioral characteristics are keystroke dynamics, voice, gait, and signature dynamics. Biometric technology are becoming for highly secure identification and personal verification. Biometric technology is now being used in almost every area. As the level of security and safety infringement and transaction scam increases, to prevent fraudulent acts and stealing of possessions and ensure safety and security thus decrease crime rates. A new supervised method for segmentation retinal vascular in retinal photographs is implemented in the project. The methods are (i) Kirsch’s Templates (ii) particle swarm optimization. The purpose of this method is to automate the retinal image biometrics. Using the retinal image biometrics the persons can be identified.
Keywords:Segmentation, Kirsch’s Templates, particles swarm optimization, Biometrics matching
INTRODUCTION
A biometric system is essentially a pattern recognition system. Today security has become important concern for the society. Societies need this security so maintain track of their daily operation and their information. To implement this security many choices are available in marketplace one of which is biometrics this document includes featured research in relation to biometrics. Bio means related to biology. Metrics indicated – The science of measurements. Fundamental operations in biometrics are Capture, Extraction, Comparison and Match or Non Match. During Capture process, raw biometric is captured by a sensing device such as a fingerprint scanner or video camera. The second phase of processing is to extract the distinguishing characteristics from the raw biometric sample and convert into a processed biometric identifier record. Next phase does the process of enrollment. Here the processed sample is stored or registered in a storage medium for future comparison during an authentication. In many commercial applications, there is a need to store the processed biometric sample only. The original biometric sample cannot be reconstructed from this identifier. Biometrics recognition types are voice print recognition first record the voice print of the person whose voice is to be recognized. The sample voice print examined for many features so that it coordinates with that sample voice print with machine. Biometrics was been founded during prehistoric time. Chinese used fingerprinting in the 14th Century for recognition. In the 17th century fingerprinting was used to seal authorized documents. Biometrics was been discovered by Francis in 1892. It actually came to be used as it had many innovations and innocence is become popular. Phases of biometrics are Input, Process and Output. Biometrics stands for the measurement of nuclear arms, Life measurements, measuring size of DNA stands and the study of whether home hold plant life will someday grow into a tree. These peculiarities are summarized by a computer and used to make one-to-one verification and one-to-many comparison based on one-off features. Biometrics was first used in during the first DPS Session, the first James Bond Movie, Prehistoric times, During the Nixon Administration. Biometric recognition requires to compare a registered or enrolled biometric sample against a newly captured biometric sample followed by a Verification or Identification process. Biometrics recognition types are voice print recognition first record the voice print of the person whose voice is to be recognized. The sample voice print is examined for many features so that it coordinates with that sample voice print with machine. The feature that mainly counts on voice print is vocal activities and the characteristics of the vocal cord. Finger print brings the print or image of the configuration of fingers and then scans them. In this kind of recognition iris which is placed behind the cornea. Iris recognition has almost 266 patterns of iris. This type of recognition uses several categories of features of face to recognize the users face. Hand geometry uses the shape of the user’s hand. Hand scanners are used to recognize the user’s hand. Retina Scan the blood vessels which are located in our eyes In this kind of recognition the user is made to enter on keyboard and the time variation between their entering keystroke is calculated and them the user is recognized.
CONCLUSION
This project is based on biometric application which I have used for identifying a person by her/his retina. I have employed the kirsch template and particle swarm optimization methods in my project as well total of 60 images were tested in my project for which the desired output was delivered for 45 images.

References:

  1. A Robust Eye Detection Method Using Combined Binary Edge and Intensity Information. Jiatao Song, Zheru Chi, Jilin Liu. Science Direct, Pattern Recognition 39 (2006) 1110-1125.
  2. A Simple and Efficient Eye Detection Method in Color Images D.Sidibe, P.Montesinos, S.Janaqi. Parc Scientifique G.Besse, France.
  3. A Hybrid Method for Eye Detection in Facial Images. Muhammed Shafi, Paul W.H.Chung. Waset. www.waset.org.
  4. Digital Image Processing. R.C. Gonzalez and R.E.Woods, 2nd edition PHI, Chapter 9, Morphological Image Processing.
  5. Handbook of Image and Video Processing. (AL Bovik) Section III, Chapter 3.3, Morphological Filtering for Image Enhancement and Detection.
  6. R.Brunelli, T.Poggio, Face Recognition, Features versus templates, IEEE Trans. Patt. Anal. Mach. Intell. 15(10)(1993) 1042-1052.
  7. D.J.Beymer, Face Recognition under varying pose, IEEE Proceedings of Int. Conference on Computer Vision and Pattern Recognition (CVPR’94), Seattle, Washington, USA,1994, pp.756-761.
  8. A.Pentland, B.Mognanddam, T.Starner, View based and modular eigenspaces for face recognition in , IEEE Proceedings of Int. Conference on Computer Vision and Pattern Recognition (CVPR’94), Seattle, Washington, USA,1994, pp.756-761.
  9. A.L.Yuille, P.W.Hallinan, D.S.Cohen, Feature Extraction From Faces Using Deformable Template, Int. J.Comput.Vision 8(2)(1992) 99-111.
  10. Robinson, S.R., ed. Emerging Systems and Technologies. SPIE: Optical Engineering Press and Environmental Research Institute of Michigan, 1993. Vol. 8 of The Infrared and ElectroOptical Systems Handbook. Eds. J.S. Accetta, D.L.Shumaker. 8 vols. 1993.
  11. Schott, J.R. Remote Sensing: The Image Chain Approach. New York: Oxford UP, 1997.
  12. Visual routines for eye location using learning and evolutionHuang, J. ; Dept. of Comput. & Inf. Sci., Indiana Univ., Indianapolis, IN, USA ; Wechsler, H.Evolutionary Computation, IEEE Transactions on (Volume:4 , Issue: 1 ) Pg-- >73 – 82 Apr 2000
  13. Face boundary extraction by statistical constraint active contour modelSun, D. ; Dept. of Radio Eng., Southeast Univ., Nanjing, China ; Zhojie Zhou ; Lenan WuSystems, Man and Cybernetics, 2002 IEEE International Conference on (Volume:6 ) Oct. 2002
  14. A 200 s Processing Time Smart Image Sensor for an Eye Tracker Using Pixel-Level Analog Image Processing Gunhee HanDept. of Electr. & Electron. Eng., Yonsei Univ., Seoul, South Korea Solid-State Circuits, IEEE Journal of (Volume:44 , Issue: 9 ) Pg-2581 – 2590 Sept. 2009’
  15. An autoregressive neural network for recognition of eye commands in an EEG-controlled wheelchairHai Thanh Nguyen ; Biomed. Eng. Dept., Int. Univ., Ho Chi Minh City, Vietnam ; Nguyen Trung ; Vo Toi ; Van-Su TranAdvanced Technologies for Communications (ATC), 2013 International Conference Pg-333 – 338 Oct. 2013