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.

  • [Show abstract] [Hide abstract]
    ABSTRACT: The need of sharing fingerprint image data in many emerging applications raises concerns about the protection of privacy. It has become possible to use automated algorithms for inferring soft biometrics from fingerprint images. Even if we cannot uniquely match the person to an existing fingerprint, revealing their age or gender may lead to undesirable consequences. Our research is focused on de-identifying fingerprint images in order to obfuscate soft biometrics. In this paper, we first discuss a general framework for soft biometrics fingerprint de-identification. We implemented the framework to reduce the risk of successful estimation of gender from fingerprint images using ad-hoc image filtering. We evaluate the proposed approach through experiments using a data set of rolled fingerprints collected at West Virginia University. Results show the proposed method is effective in preventing gender estimation from fingerprint images.
    2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO); 05/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we investigate the possibility of using limited feature points (shape landmarks) from 3-D human body shapes to recognize the gender of human beings. Several machine learning algorithms and feature extraction algorithms (principal component analysis and linear discriminant analysis) are investigated and analyzed in this paper. Experimental results on a large dataset containing 2484 3-D shape models show that limited feature points (shape landmarks) can be used for gender recognition and can achieve high recognition rate, which provides a fast gender recognition technique. The research provides a potential research direction for gender recognition.
    Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on; 01/2012
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent times, some studies have explored the forensic application of dermatoglyphic traits such as the epidermal ridge breadth or ridge density (RD) toward the inference of sex and population from fingerprints of unknown origin, as it has been demonstrated that there exist significant differences of fingerprints between sexes and between populations. Part of the population differences found between these studies could be of methodological nature, due both to the lack of standardisation in the position of the counting area, as well as to the differences in the method used for obtaining the fingerprint. Therefore, the aim of this study was to check whether there are differences between the RD of fingerprints depending on where the counting area is placed and how the fingerprints are obtained. Fingerprints of each finger were obtained from 102 adult Spanish subjects (50 females and 52 males), using two methods (plain and rolled). The ridge density of each fingerprint was assessed in five different areas of the dactylogram: two closer to the core area (one on the radial and the other on the ulnar side), two closer to the outermost area of each of the sides (radial and ulnar), and another one in the proximal region of the fingertip. Regardless of the method used and of the position of the counting area, thumbs and forefingers show a higher RD than middle, ring, and little fingers in both sexes, and females present a higher RD than males in all areas and fingers. In both males and females, RD values on the core region are higher than those on the outer region, irrespective of the technique of fingerprinting used (rolled or plain). Regardless of the sex and location of the count area (core or outer), the rolled fingerprints exhibit RD greater than that of the plain ones in both radial and proximal areas, whereas the trend is inverted in the ulnar area, where rolled fingerprints demonstrate RD lesser than that of the plain ones. Therefore, in order for the results of different studies to be comparable, it is necessary to standardise the position of the count area and to use the same method of obtaining the fingerprint, especially when involving a forensic application.
    Science & Justice 01/2013; 54(3). DOI:10.1016/j.scijus.2013.11.004 · 1.42 Impact Factor