Spoofed Fingerprint Detection Based on Time Series Fingerprint Image Analysis
Shefali Arora, Naman Maheshwari, M. P. S. Bhatia · 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC) · 2018
The primary purpose of fingerprint recognition is to make sure that user authentication is reliable. Fully connected Convolutional networks help to attain good performance in classifying a time-series sequence of captured fingerprint images. In this paper, we work on the approach of detecting spoofed fingerprints from these sequences by combining the use of Convolutional Neural Networks and Long Short Term Memory networks. Our proposed model has superior performance, with minimum amount of processing and optimal model size. The experiments, carried out on a dataset [1] of real and spoofed fingerprints, prove that the proposed approach is effective in detecting spoofed fingerprints.