A simple approach for biometrics: Finger-knuckle prints recognition based on a Sobel filter and similarity measures

2026-05-17

AI Summary

This study explores finger knuckle prints as a novel biometric modality for identity verification and proposes a lightweight, efficient recognition approach. The method employs the Sobel operator for edge extraction, followed by simple noise reduction and binarization to construct a low-memory, rapid visual processing pipeline. One-to-one matching is achieved through multiple similarity metrics. Evaluated on a large-scale dataset, the system attains a true positive identification rate of 17.02%, demonstrating the feasibility and potential of minimalist algorithmic design in finger knuckle print recognition.

Abstract

The objective of this work is to propose a novel methodology for the finger knuckle print recognition, which is essentially a digital photo of the finger-knuckle region. We have employed very simple concepts of visual computing such as a filter based on the Sobel operator for finding edges and a simple noise reduction algorithm. These operations are exceptionally fast and produce binary images, which are very efficient to process and to store. Furthermore, alongside this preprocessing, some similarity measures were also regarded and evaluated for the task. After preprocessing an input finger it is compared to all the images of fingers in the dataset, one by one. We have obtained up to 17.02% of successful recognitions (true positive rate) with a large dataset.

Problem

• finger-knuckle print recognition
• biometrics
• similarity measures
• edge detection
• image preprocessing

Innovation

• finger-knuckle print recognition
• Sobel filter
• similarity measures
• binary image preprocessing
• biometric authentication