Convolutional neural network based children recognition system using contactless fingerprints

Abstract

Biometric features are useful for unique identification, authentication, and security applications. Among all biometric features, fingerprints are the most commonly used because they contain ridges and valleys. There are challenges in recognizing child or infant fingerprints since the ridges are not mature as the hands are covered with a white substance and acquisition of fingerprint images is difficult. In the context of COVID-19 pandemic, contactless fingerprint acquisition gains importance as it is not infectious especially with children. In this study, a Convolutional Neural Network (CNN) based children recognition system named Child-CLEF, that uses Contact-Less Children Fingerprint (CLCF) dataset acquired using a mobile phone-based scanner is proposed. The quality of captured fingerprint images is enhanced using a hybrid image enhancement method. Furthermore, the minutiae features are extracted using the proposed Child-CLEF Net model and the identification of children is made using a matching algorithm. The proposed system is tested with a self-captured children fingerprint dataset, CLCF and publicly available PolyU fingerprint dataset. It is found that the proposed system outperforms the existing fingerprint recognition systems in terms of accuracy and equal error rate.

Features Understanding for Contactless and Contact-Based Fingerprint Matching

“…Score-level fusion is performed to achieve improved accuracy. Rajaram et al [26] proposed a CNN-based Child recognition system "Child-CLEF" for contactless fingerprint matching. A novel fusion score is obtained using wavelets, and minutiae matching with the deep-learning method.…”