Fingerprint Classification Using Deep Convolutional Neural Network

Fingerprint classification is a method of reducing the number candidates needed by fingerprint recognition systems to determine if picture matches one in database. Deep learning has gained lot attraction recent decade including natural language processing, digital image speech recognition, handwritten digit medical assessments, and so on. The subject this paper explore factors affecting using convolutional neural network train test deep CNN model, model includes two serial stages, preprocessing phase which used enhance images qualities, post-processing model. This been accomplished designing new for work. Convolutional achieved outstanding accuracy on fingerprint. experiment NIST DB4 dataset contains 4,000 fingerprints with five labels. Separately, each label database comprises almost 800 samples dimension 512 x 512. To lower training time required we reduced up 200 dimension. study achieves 99.2% zero-rejection rate.