A Novel Method for Gender Classification Using DWT and SVD Techniques

In today’s time fingerprint plays a very important role, whether it is to link the suspect in a crime scene or to find an unknown person. Fingerprints are one of the most mature biometric technologies and are considered legitimate proofs of evidence in courts of law all over the world. The main objective of this paper is to find a link between gender of a person and his/her fingerprint. The gender of an unknown fingerprint was found out by classifying the frequency and spatial domain vector of the input image. The 2D-Discrete Wavelet Transformation (DWT) was used to find the frequency domain vector and Singular Value Decomposition (SVD) was implemented in order to find the spatial feature of the non-zero singular values. Both the outputs of SVD and DWT are combined to form the feature vector. The K-nearest neighbour classifier is used to classify the fingerprint. The method is experimented with the internal database of 100 fingerprints of left hand index finger, 50 males and 50 females belonging to same age group. Keywords— Fingerprint, Biometric technologies, Discrete Wavelet Transformation, Singular Value Decomposition, Knearest neighbour classifier.