Contactless palmprint recognition: A mini review

Abstract

The increasing terrorist and criminal acts on public, private, and government
\ninfrastructure have resulted in a chaotic situation, thereby putting the surveillance
\nsystem in existence under pressure. Conventionally, information systems rely on users
\nto remember their secret pins (passwords) or tokens, cards, or both to confirm their
\nidentity. In order to achieve this in modern times, personal identification is based on the
\nbehavioral or physiological traits of individuals. These attributes known as biometrics
\nrefer to the unique physiological (e.g., palmprint, fingerprint, face, iris, etc.) or behavioral
\n(e.g., gaits, signature, voice, etc.) traits used for automatic recognition. These biometric
\ntraits offer many advantages over knowledge and possession-based approaches. For
\ninstance, palmprint images have rich, unique features for reliable human identification,
\nand they have received significant research attention due to their stability, reliability, and
\nuniqueness, which makes them a competitive area of research. This paper provides a
\nmini overview of contactless palmprint recognition systems as well as preliminary
\nfindings. The various types of Region of Interest (ROI) extraction algorithms, feature
\nextraction, and matching algorithms are well discussed. In addition, the state-of-the-art
\nperformance of existing works is presented.