Conference Paper

Fingerprint-Based Gender Classification.

Conference: Proceedings of the 2006 International Conference on Image Processing, Computer Vision, & Pattern Recognition, Las Vegas, Nevada, USA, June 26-29, 2006, Volume 1
Source: DBLP

ABSTRACT Gender classification 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. A dataset of 10-fingerprint images for 2200 persons of different ages and gender (1100 males and 1100 females) was analyzed. Features extracted were; ridge count, ridge thickness to valley thickness ratio (RTVTR), white lines count, ridge count asymmetry, and pattern type concordance. Fuzzy C- Means (FCM), Linear Discriminant Analysis (LDA), and Neural Network (NN) were used for the classification using the most dominant features. We obtained results of 80.39%, 86.5%, and 88.5% using FCM, LDA, and NN, respectively. Results of this analysis make this method a prime candidate to utilize in forensic anthropology for gender classification in order to minimize the suspects search list by getting a likelihood value for the criminal gender.

0 Bookmarks
 · 
128 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Although several studies have recently assessed sex differences in fingerprint ridge density and its variability in human populations from different origins, such a study has not been carried out yet in the Amerindian population. The goal of this study was to determine the topological and sexual differences in fingerprint ridge density (RD) in native subjects from two samples of northwestern Argentina (Jujuy province) living at different altitudes. The results were compared with those obtained from a Spanish population sample. The study was based on data from all 10 fingerprints of 393 adult Argentinian men and women, 193 from the Puna-Quebrada region (more than 2500 m above sea level) and 200 from Ramal (500 m above sea level). Ridge density was assessed for three different areas (radial, ulnar and proximal) for all 10 fingers of each subject. In both samples, significant differences between areas were obtained, so radial RD > ulnar RD > proximal RD. No significant differences were found between samples in males, while females from both samples significantly differed in the radial and proximal areas. Females have higher RD, so narrower ridges, than men, in all areas and all fingers. Application of Bayes' theorem allowed us to obtain a ridge density threshold for discrimination of sexes in Argentinian samples and the threshold for discrimination of populations between Argentinian and Spanish samples. These results can be useful for forensic use.
    Journal of forensic and legal medicine 07/2013; 20(5):419-29.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel method of gender Classification from fingerprint is proposed based on discrete wavelet transform (DWT) and singular value decomposition (SVD). The classification is achieved by extracting the energy computed from all the sub-bands of DWT combined with the spatial features of non-zero singular values obtained from the SVD of fingerprint images. K nearest neighbor (KNN) used as a classifier. This method is experimented with the internal database of 3570 fingerprints finger prints in which 1980 were male fingerprints and 1590 were female fingerprints. Finger-wise gender classification is achieved which is 94.32% for the left hand little fingers of female persons and 95.46% for the left hand index finger of male persons. Gender classification for any finger of male persons tested is attained as 91.67% and 84.69% for female persons respectively. Overall classification rate is 88.28% has been achieved.
    05/2012;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Despite the fact that variation in ridge breadth is of biological, medical, and genetic interest, it has not received as much attention as other dermatoglyphic characteristics. Recently, sex differences in mean epidermal ridge breadth have been proposed in the field of forensic identification in order to infer gender from fingerprints found at the scene of a crime left by an unknown donor. The aim of this research was to analyze sexual, bimanual, and topological variations in epidermal ridge breadth on palmprints taken from a Spanish population sample for subsequent application in inferring gender from the palm marks. The material used in the present study was obtained from the palmprints of 200 individuals (100 males and 100 females) from the Caucasian Spanish. Since ridge breadth varies according to age, subjects of similar ages were recruited to ensure that growth had finished. Therefore, in order to assess topological variation in ridge density or number of ridges in a given space, the count was carried out for the five palmar areas: hypothenar, thenar/first interdigital, second interdigital, third interdigital, and fourth interdigital. This allowed the segmentation of 2000 ridge count areas for analysis. For this, two methods were used, one described by Cummins et al. (the ridge count was carried out along a 1cm line) and the other by Acree (the number of ridges per 25mm(2) of surface area). The results obtained by the second method can be compared with those obtained for the ten fingers from this same sample and evaluated in a previous study. The results have demonstrated the existence of topological differences in ridge thickness on the epidermal palm surface; also females present a significantly higher ridge density than men and, therefore, have narrower ridges over the entire palmar surface. Those sexual differences found in the sample population can be used for inferring the gender from palm marks left by an unknown donor. The hypotheses that could explain the variability in ridge breadth are evaluated according to the obtained results.
    Forensic science international 04/2013; · 2.10 Impact Factor

Full-text

View
66 Downloads
Available from
May 22, 2014