Feature extraction of finger-vein patterns based on boosting evolutionary algorithm and its application for loT identity and access management

Abstract

With billions of devices being connected, how to make sure that our information stays secure is becoming a hot topic of IoT. Traditional approaches to personal authentication are inadequate and ineffective in the IoT era. Finger vein technology is the current biometric system that utilizes the vein structure for recognition. As such patterns are veiled under the skin surface, they have significant privacy protection and are therefore incredibly difficult to forge. Finger vein recognition has gained a great deal of publicity because earlier approaches experienced significant pitfalls, such as its inability to handle the imbalanced collection of finger veins samples and the detection of distinguishing features in low-quality images. Such disadvantages have triggered a lack of consistency of the optimization algorithm or have contributed to a decrease in its efficiency. The key objective of the research discussed in this paper is to examine the impact of the genetic algorithm in the selection of the optimum vector characteristics of the finger vein. This is done by incorporating a Niching model in the form of a Context-Based Clearing (CBC) procedure to increase the heterogeneity of the features within the features’ vector, with the goal of minimizing the association between them. It also offers the idea of a reduction of the feature set to reduce duplication without reducing accuracy. The performance study of the proposed model is carried out through multiple tests and the findings indicate an overall increase of 6% in the accuracy relative to some of the state-of-the-art finger vein recognition systems present in the literature.