A novel fingerprint classification system using BPNN with local binary pattern and weighted PCA

Fingerprint classification is an important indexing scheme to reduce fingerprint matching time. In this paper, a novel approach to classify fingerprint images is proposed. It involves four main parts: denoising, feature extraction, dimensionality reduction and classification. Initially, the fingerprint is denoised using undecimated wavelet transform. Then short time Fourier transform (STFT) is used to enhance the denoised fingerprints. A set of local binary pattern (LBP) features are extracted to overcome the difficulty associated with singular point detection. To reduce the dimensionality of the feature space, quick reduct (QR), principal component analysis (PCA) and weighted PCA have been investigated. Finally, the fingerprint images are classified using back propagation neural network (BPNN). In this research, experiments have been conducted on real-time fingerprint images collected from 150 subjects and also on the NIST-4 dataset. The proposed method has been compared with support vector machine (SVM), K-nearest neighbor (K-NN), and multi-layer perceptron (MLP).