A practical person authentication system using second minor finger knuckles for door security

Abstract

This paper proposes a person authentication system using second minor finger knuckles, i.e., metacarpophalangeal (MCP) joints, for door security. This system acquires finger knuckle patterns on MCP joints when a user takes hold of a door handle and recognizes a person using MCP joint patterns. The proposed system can be constructed by attaching a camera onto a door handle to capture MCP joints. Region of interest (ROI) images around each MCP joint can be extracted from only one still image, since all the MCP joints are located on the front face of the camera. Phase-based correspondence matching is used to calculate matching scores between ROIs to take into consideration deformation of ROIs caused by hand pose changes. Through a set of experiments, we demonstrate that the proposed system exhibits the efficient performance of MCP recognition and also show the potential possibilities of second minor finger knuckles for biometric recognition.

Multimodal Biometric Recognition Based on Convolutional Neural Network by the Fusion of Finger-Vein and Finger Shape Using Near-Infrared (NIR) Camera Sensor

“…Aoyama et al conducted a band-limited phase-only correlation (BLPOC)-based local block matching that features higher correlation as becoming more similar images by extracting elliptic frequency bands that show the ridges of finger knuckle prints through the cross-phase spectrum calculations in phase-only correlation (POC) functions [ 9 ]. In [ 10 ], it was confirmed that the finger knuckle-print patterns of metacarpophalangeal (MCP) joints could be recognized while using BLPOC as well.…”

“…However, in the case of people with certain skin conditions, feature extraction might be difficult while using image processing. To solve this problem, a study was conducted on finger knuckle-print matching methods [ 7 , 8 , 9 , 10 ]. Aoyama et al conducted a band-limited phase-only correlation (BLPOC)-based local block matching that features higher correlation as becoming more similar images by extracting elliptic frequency bands that show the ridges of finger knuckle prints through the cross-phase spectrum calculations in phase-only correlation (POC) functions [ 9 ].…”

Phase-Based Periocular Recognition with Texture Enhancement

“…Phase-based image matching has shown to be effective for recognizing popular biometric traits such as fingerprint [32], iris [33], palmprint [12], [34], and finger knuckle [35], [36], which contain homogeneous texture components. When we apply phase-based image matching to periocular recognition, however, we have to deal with heterogeneous texture components contained in periocular images.…”

[Invited Paper] Recent Advances in Biometric Recognition

“…3. We have developed a practical person authentication system using PIP joints 63)76) and MCP joints 77) for door security. Finger knuckle patterns can be captured by a camera when a user takes hold of a door handle.…”

“…PIP joints have rich texture, resulting in better recognition accuracy than MCP joints, while all the PIP joints are not always faced toward a camera due to the structure of a hand 63)76) . All the MCP joints can be extracted from the captured image, resulting in more stable than PIP joints, while nonlinear deformation of MCP joints has to be addressed to obtain good performance 77) . The accuracy of PIP joint recognition is good, although all the PIP joints are not always extracted from only one still images 76) .…”