Discriminant Analysis and Naïve Bayes Classifier-Based Biometric Identification Using Finger Veins

Discriminant Analysis and Naïve Bayes Classifier-Based Biometric Identification Using Finger Veins

Insha Qayoom (Department of Computer Science and Engineering, SEST, Jamia Hamdard, New Delhi, India) and Sameena Naaz (Department of Computer Science and Engineering, SEST, Jamia Hamdard, New Delhi, India)
Copyright: © 2019 |Pages: 13
DOI: 10.4018/IJCVIP.2019100102
OnDemand PDF Download:
No Current Special Offers


Finger vein identification is a dominating method of biometric technology used for authentication in a highly secure environment. Vein patterns are unique for each individual and it is underneath skin so there is less chance for forgery. In the current research work, finger vein features are extracted and verified for the purpose of authentication. The first step in this work is to pre-process the image obtained from the database. In order to get the region of interest (ROI) the threshold value is calculated using a standard deviation method followed by morphology-based functions available in the MATLAB software. After pre -processing a Gabor filter, fast filter, and freak descriptors are used. The features calculated at the freak descriptor processing are trained on classifiers namely discriminant and Naïve Bayes. The features trained to the classifiers are then fed again into the classifiers and cross verified to update the results of accuracy. The accuracy calculated using discriminant analysis is 94.46% and by using Naïve Bayes is 98.38%.
Article Preview

1. Introduction

Biometric is an innovation used to verify people by using the uniqueness of one’s physical features. The individual recognizing verification system has introduced improvement to a large extend. Generally, PINs, passwords, key etc. are used for security frameworks. However, these confirmation modes are forgotten easily. Also, the financial losses due to identity theft can be damaging. All these issues are fairly taken care of by using biometric pattern. Unique finger impression (Rajkumar & Hemachandran, 2011), iris, face and so forth are the biometric patterns. Each of these biometric characteristics has its inadequacies. They cannot be stolen but certain people’s fingerprints can be worn away or sweat-soaked and cannot be enrolled. Iris biometric pattern are less prone to attacks and are more accurate, but the disadvantage is that some clients cannot tolerate the direct light into their eyes. With respect to face and voice acknowledgment, they are the methods by which people remember each other in regular social connection and are in this way the most natural types of individual identification with limited accuracy rate. Regarding security and comfort, finger vein is a remarkable biometric design (Liu & Song, 2012).

In this pattern, blood vessels are covered inside the body and also the clients have no physical contact with the system, that increases its complexity and security and is a greater challenge for those who want to defeat them. This technology is used in the field of financial, medical, law requirement office and where high-level security is necessary.

The upsides of finger veins are:

  • 1.

    Live body recognizable proof;

  • 2.

    Infrared camera can catch finger vein pictures just if deoxygenated hemoglobin is available in the body and the imaging must be done from live body. This will give additional security;

  • 3.

    High security: Unlike the vast majority of the biometric designs being used like fingerprint, palm print, face recognition, iris and so forth, the vein is seen inside the body and is hard to forge (Hashimoto, 2006);

  • 4.

    Vein patterns are different for different fingers and also varies among individuals. In fact, twins also have different vein patterns. Even their false acknowledgment rate is low (near zero) (Lee, Lee, & Park, 2009).

Finger vein authentication therefore offers substantially more benefits as compared to the other forms of biometrics. One of the most important characteristics of this type of authentication is that it offers a high accuracy that at the same time is almost impossible to counterfeit.

As the finger vein blood vessels are present inside the body so it is not easy for any camera to capture its image. Image captured for finger veins depends on the principle of light reflection or light transmission. So, a special NIR camera is used in order to capture a high-quality image. NIR light can easily go through the bones of finger regardless of the bone thickness. The flow of this paper is sorted out as follows. In section II literature review has been done. Section III discusses the proposed work. It consists of pre-processing of image by segmentation and enhancement technique. Here, the region of interest (ROI) is obtained by segmentation. In section IV the implementation details are discussed. Section V shows all the results and their discussions Conclusion from this paper are finally discussed in section VI.


From the recent past a number of strategies have been produced for the distinctive finger vein image enhancement and for feature extraction. The biometric distinguishing proof from finger vein outlines using association of finger vein pictures was proposed by (Kono, Ueki, & Umemura, 2007). In this strategy, enhancement in vein patterns was done by background-reduction filter i.e. a low pass filter was used to diminish the background noises. The inconvenience of this technique is that when the background noises were diminished, some relevant information from the nearer view was filtered through.

Complete Article List

Search this Journal:
Volume 12: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing