Fingerprint Based Gender Classification Using DWT Transform

Each person's fingerprint structure is unique and is developed for bio-metric authentication systems than others because fingerprints have advantages such as: feasible, differ from each other (distinct), permanent, accurate, reliable and acceptable all over the world for security and person identity. Fingerprints are considered as legal proof of evidence in courts of law all over the world. Frequency domain based fingerprint classification can be done using discrete wavelet transform (dot), which uses wavelet as its basis function which gives energy based features of an image. We are taking dataset of 100 male and 100 female fingerprints. K nearest neighbor (knn) classifier is used as a classifier which uses Euclidean Distance measure for classification and classifies testing fingerprint as male or female fingerprint. This paper describes the overall process of above scheme. DWT transform will give the features of some of the fingerprint images of dataset (training images) to create database of features which will be used as look up table for classification of unknown fingerprint and other fingerprints (testing fingerprints) will be used for testing. Knn classifier will assign one of two groups to testing fingerprint.