ISSN (Print): 2328-3491, ISSN (Online): 2328-3580, ISSN (CD-ROM): 2328-3629
American International Journal of
Research in Science, Technology,
Engineering & Mathematics
AIJRSTEM 15-126; © 2015, AIJRSTEM All Rights Reserved Page 39
AIJRSTEM is a refereed, indexed, peer-reviewed, multidisciplinary and open access journal published by
International Association of Scientific Innovation and Research (IASIR), USA
(An Association Unifying the Sciences, Engineering, and Applied Research)
Available online at http://www.iasir.net
Fingerprint Based Gender Classification for Biometric Security: A State-
Of-The-Art Technique
Shivanand. S. Gornale
Department of Computer Science, School of Mathematics and Computing Sciences, ,
Rani Channamma University, Belagavi, Karnataka, INDIA.
I. Introduction
The science of fingerprint has generally been used for the identification or verification of a person for official
documentation. There are many biometric techniques like Fingerprints, Hand Geometry, Retina Scanning, Iris
Scanning, Face Recognition analysis, DNA fingerprint, Signature, Voice, Key Stroke Pattern, Gait (Body
Dynamics),etc., A few of them are in the stage of research only (e.g., the odour analysis), but a significant
number of techniques are already mature and commercially available.
Fingerprint Identification and Verification is certainly the most reliable and adequate evidence till date in the
court of law. Basically, the skin of human fingertips consists of ridges (this does not change over the time and is
unique to a person) and valleys which constitute a distinctive pattern which is composed of many ridges and
furrows. The fingerprint pattern, when analyzed at different scales, exhibits different types of features called
Macro-Characteristic of Fingerprints and Micro-Characteristics of Fingerprints.
The macro-characteristics are global features constituted by the ridge pattern and the singularity points. The
ridge pattern characterizes the shape described by the ridge flow. The singularity points are localized in small
regions where the ridge flow becomes irregular. Human fingerprint is comprised of a varied variety of ridge
pattern, historically these are classified into (a) Arch (b) Tented Arch (c) Left Loop (d) Right Loop (e) Whorl.
These are shown in figure-1. Core and delta points are shown for each class in this figure by circle and triangles,
respectively.
Figure-1.1 (a) Arch (b) Tented Arch (c) Left Loop (d) Right Loop (e) Whorl.
Abstract: Fingerprint Identification and Verification are certainly the most reliable and adequate evidence
till date in the court of law. There are many biometric techniques like Fingerprints, Hand Geometry,
Retina Scanning, Iris Scanning, Face Recognition, DNA fingerprint, Signature, Voice, Key Stroke Pattern,
Gait (Body Dynamics),etc., that play a crucial role in identification and verification. The fingerprint
biometric is one among most researched and used techniques for identification and verification.
Comparatively a small number of machine vision techniques have been suggested for gender recognition
and classification. So identifying the gender from fingerprints is an important step in forensic
anthropology to shorten the list of suspects search. Very few researchers have worked on gender
classification using fingerprints and have gained competitive results. This paper presents a comprehensive
evaluation of lstate-of-the-art research techniques associated with gender classification using fingerprints
and it is also proposed to combines the elaborate study of various methods and strategies with their
comparative measures and to forecast results. This will help the researcher to undertake a comprehensive
review and to carry out further research in fingerprint-based gender classification for biometric security.
Key words: Gender classification, Minutia extraction, Image-based methods, Minutia based methods,
feature classification.