Damaged fingerprint classification by Deep Learning with fuzzy feature points

As the world enters the information age, the need for identity verification becomes more and more urgent. Therefore, fingerprint identification technology is widely used in the field of personal authentication. With the efforts of researchers, the algorithms of fingerprint recognition have currently made great progress. However, the authentication of low quality fingerprint still needs further improvement. Aiming at imperfect fingerprints, we propose an improved damaged fingerprint recognition algorithm by feature points, based on Convolution Neural Network (CNN) of Deep Learning. Finally, the recognition rate based on Deep Learning is compared with the fingerprint identification algorithm based on Kernel Principal Component Analysis (KPCA) and k-Nearest Neighbor (KNN). Experiments' results show that fingerprint recognition based on Deep Learning has a higher recognition rate.