Analysis of Fingerprint Image for Gender Classification or Identification: Using Wavelet Transform and Singular Value Decomposition

Fingerprint evidence is undoubtedly the most reliable and acceptable evidence till date in the court of law. Fingerprints are obtained at the site of crime and in many old monuments and in excavated things. Estimating the gender of fingerprints is an emerging field and many methods using the fingerprint physical features like the ridge count and the ridge thickness have been used so far. Due to the immense potential of fingerprints as an effective method of identification an attempt has been made in the present work to analyze their correlation with gender of an individual using discrete wavelet transform(DWT) and singular value decomposition (SVD). The classification as per gender 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 [1]. Our aim is to use this method with the internal database of 1000 finger prints in which 500 samples will be male fingerprints and 500 samples will be female fingerprints. We will analyze the results which are expected as follows: 1. Finger-wise gender classification for the left hand little fingers of female persons - 82.60% for the left hand index finger of male persons - 82.90%. Gender classification for any other finger of male persons tested is attained as 80.40% and 76.84% for female persons respectively.