Fingerprint image classification based on deep learning
Yafang Bai, Yanfeng Tang, Di Xia, Peng Wang, Che Liu, Wenjie Yan, Chen Wang · 2022
A fingerprint image classification method based on improved Res Net was proposed through experimental research. We take the existing fingerprint data set as object, expand the number of sample images by combining data enhancement technology, finally four kinds of labels are classified according to the global characteristics of fingerprints. The new net structure was built based on convolutional neural network, and iterative optimization was carried out by SGD. Classification accuracy and training rounds were evaluated by comparing the experimental results of different networks. To verify the applicability of the proposed method, 11824 sample images were composed of four kinds of data for training and testing. The results show that after 100 times of iterative training, the accuracy of fingerprint image classification for four kinds of data is above 95.7%, and the highest is 97.4%. This method supports high precision classification of mixed fingerprint images and has good practical.