A systematic review of end-to-end framework for contactless fingerprint recognition: Techniques, challenges, and future directions

Contactless fingerprint biometrics have seen rapid advancements in the recent years due to its intrinsic advantages such as resilience against latent fingerprints, and enhanced hygiene due to the absence of physical contact between a finger and the sensor. These advantages boosted the development of novel techniques for contactless fingerprint recognition. An exponentially increasing number of publications related to these developments are becoming part of the literature. However, no systematic review that consolidates these developments has been presented to date, thereby leaving a significant void. Hence, there is a need to fill this void by presenting a comprehensive review of contactless fingerprint biometric technology. A review of this kind will be highly beneficial for individuals keen on pursuing research in this domain. This study presents a systematic review of the methods used in an end-to-end framework for contactless fingerprint recognition, including acquisition, segmentation, enhancement, feature extraction, and matching, using both traditional and deep learning techniques. As per the review protocol and inclusion-exclusion criteria, 112 papers have been finally included in this review. The primary focus of the review is to present the underlying methods, their reported performance outcomes, and their strengths and weaknesses. The review evaluates the recent research findings, highlights the research issues that have been effectively addressed, presents the biases in the studies, identifies ongoing challenges that remain in the field, and provides the future research directions.