ANALYSIS OF FINGERPRINT IMAGE FOR GENDER CLASSIFICATION USING SPATIAL AND FREQUENCY DOMAIN ANALYSIS
Shivanand S. Gornale, R Kruthi · 2013
Gender identification from fingerprints is an important step in forensic anthropology in order to identify the gender of a criminal and minimize the list of suspects search. Fingerprint identification and classification has been extensively researched in the literature however very few researchers have studied the fingerprint gender classification problem. In this paper, gender identification is carried out by using combined features like FFT, Eccentricity and Major Axis Length. Left thumb impression of each sample of the internal database of 450 male samples and 550 female samples of good quality are selected. An optimal threshold for each transform is chosen for better results. It is found that the proposed algorithm produces accurate decision of 80% of male and 78% of female. The overall performance of the system is found to be satisfactory and useful to forensic anthropology.