Biometrics and Bioinformatics

Nitin Niwariya ¹, R. S. Anand ¹, M. L. Dewal ¹

Affiliations
1 Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee-247667, Uttarakhand, IN

Abstract

The retinal fundus images are normally used by the eye specialist for the diagnosis and treatment of various eye diseases like Diabetic retinopathy and Glaucoma. The blood vessel patterns are not clearly visible in the retinal fundus image so the eye specialist requires a laborious analysis for inspection of retinal vasculature, in order to detect any major change in the blood vessel structure which is caused due to eye diseases. This paper presents a performance comparison of retinal blood vessel enhancement obtained using 2-D Gabor wavelet transform technique and Morphological enhancement technique. We used both the techniques on the STARE database and DRIVE database. We obtained best enhancement results by 2-D Gabor Wavelet method. Evaluation of the retinal image enhancement methods are performed by calculating Universal Quality Index and Structure Similarity Index of enhanced images.

Keywords

Fundus Images, Vessel Enhancement, Vascular Pattern.

Full Text

     

Kalpana Saini ¹, M. L. Dewal ², Rajeev Kumar ³

Affiliations
1 Electrical Engineering Department, The Indian Institute of Technology, Roorkee, IN
2 Electrical Engineering Department, The Indian Institute of Technology, Roorkee, IN
3 Instrumentation and Control Engineering Department, Galgotia College of Engineering & Technology, Greater Noida, IN

Abstract

We have taken Biometrics i.e. fingerprint for this purpose which is the most reliable security tool for security of the system Fingerprint recognition has long been favored among many biometric identification technologies due to its uniqueness and permanence. Nowadays, fingerprint recognition is considered to be the best choice for most applications from network security systems to compact devices, due to its accuracy, speed, reliability, non-intrusive interfaces, and cost-effectiveness. We have made a fingerprint matching system using MATLAB. After collecting the database we provide a security to a virtual process that has been designed in LABVIEW and make an efficient HMI. The fingerprint recognition system may suffer attacks at different points during the authentication process. Sometimes the fingerprints gives 100% matching but it may be false fingerprint. The most common attacks occur by the use of fake fingerprint during the capture of image. The transmission channel between the feature extractor and matching may also be intercepted and the fingerprint feature may be stored for the later use. The main problem relies on how to differentiate a live finger from that one made of some synthetic material. In This Paper we discuss the all such type of attacks as well as some other interesting and other topics related to fingerprints like these may be damage or stolen by some person and effect of illness to them. This paper gives an approach to remove such type of attacks by using a virtual system. Along with this virtual system some aspects related to secure fingerprint is also be considered in this paper.

Keywords

Authentication, Biometrics, Fingerprint Recognition, HMI.

Full Text