Shoichiro Aoyama

Finger-Knuckle-Print recognition using BLPOC-based local block matching

This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching is successfully applied to image recognition tasks for biometric authentication applications. To calculate the matching score, the proposed algorithm corrects the global and local distortion between FKP images using the BLPOC-based local block matching. Experimental evaluation using the PolyU FKP database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional algorithms.

A finger-knuckle-print recognition algorithm using phase-based local block matching

This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching, is successfully applied to image recognition tasks for biometric recognition applications. To calculate the matching score, the proposed algorithm corrects the global and local deformation between FKP images using phase-based correspondence matching and the BLPOC-based local block matching, respectively. Experimental evaluation using the PolyU FKP database demonstrates the efficient recognition performance of the proposed algorithm compared with the state-of-the-art conventional algorithms.

Palm region extraction for contactless palmprint recognition

Palm region extraction is one of the most important processes in palmprint recognition, since the accuracy of extracted palm regions has a significant impact on recognition performance. Especially in contactless recognition systems, a palm region has to be extracted from a palm image by taking into consideration a variety of hand poses. Most conventional methods of palm region extraction assume that all the fingers are spread and a palm faces to a camera. This assumption forces users to locate his/her hand with limited pose and position, resulting in impairing the flexibility of the contactless palmprint recognition system. Addressing the above problem, this paper proposes a novel palm region extraction method robust against hand pose. Through a set of experiments using our databases which contains palm images with different hand pose and the public database, we demonstrate that the proposed method exhibits efficient performance compared with conventional methods.

Similarity Measure Using Local Phase Features and Its Application to Biometric Recognition

In the field of biometric recognition, similarity measure using local features such as Gabor-based coding, Local Binary Patterns (LBP) and Scale Invariant Feature Transform (SIFT) has been applied to various biometric recognition problems. These features, however, may not always exhibit higher recognition performance than the recognition algorithms of the specific biometric trait. In this paper, we propose a novel similarity measurement technique using local phase features for biometric recognition. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images exhibits good performance for evaluating the similarity between images. The local phase features extracted from multi-scale image pyramids can handle nonlinear deformation of images. Through a set of experiments in some biometric recognition such as face, palmprint and finger knuckle recognition, we demonstrate the efficient performance and versatility of the proposed features compared with the state-of-the-art conventional algorithms.

Multi-finger knuckle recognition from video sequence: Extracting accurate multiple finger knuckle regions

This paper presents a multi-finger knuckle recognition system and proposes a finger knuckle region extraction algorithm from a video sequence. The use of video sequences makes it possible to achieve stable and robust finger knuckle region extraction, since the optimal image frame can be selected from a set of image frames to extract a region to be matched for each finger. Through a set of experiments, we demonstrate that the extraction rates of the proposed algorithm are 96.4%, 99.4%, 97.6% and 96.4% for index, middle, ring and little fingers, respectively, which are acceptable in practice. The result indicates that four fingers can be used for person authentication in most cases. We also demonstrate that the use of multiple finger knuckle regions exhibits efficient performance for person authentication.

A multi-finger knuckle recognition system for door handle

This paper proposes a multi-finger knuckle recognition system for a door handle. The proposed system consists of simple hardware such as a camera and a near-infrared light source. This paper has also proposed a baseline recognition algorithm for multi-finger knuckles. The proposed algorithm consists of the region of interest (ROI) extraction and ROI matching. From the captured image, the ROI around phalangeal joint is extracted using vertical and horizontal projections. There is a large deformation between extracted ROIs due to the position of hand. To address a large deformation, the proposed algorithm employs the phase-based correspondence matching to evaluate the similarity between ROIs. Through a set of experiments, we demonstrate that the proposed baseline algorithm exhibits good performance compared with the conventional finger knuckle recognition algorithms.

Disaster victim identification using dental records — Experience of the Great East Japan Earthquake

This paper reports basic methods of victim identification actually used in the Great East Japan Earthquake and Tsunami on March 11, 2011. In this disaster, it was proved that dental identification is very effective compared with other biometric identification methods such as fingerprint/palmprint identification and DNA-based identification. We designed and implemented a workflow of dental identification in close cooperation with Miyagi Prefectural Police and Miyagi Dental Association. We also discuss the possibility of advanced techniques for disaster victim identification using dental radiographs and CTs.

A Contactless Palm Recognition System Using Simple Active 3D Measurement with Diffraction Grating Laser

In contact less palm recognition, the captured images may have large image deformation depending on the hand pose. In order to extract the accurate palm region from the captured image for reliable palm image matching, such large image deformation must be normalized. To address the above problem, we propose a contact less palm recognition system using simple active 3D measurement with a diffraction grating laser. Using the grating pattern on a hand, which is radiated by the diffraction grating laser, the sparse 3D structure of hand surface can be measured by triangulation among a hand, a laser and a camera. According to the hand structure, the image deformation caused by the hand pose change can be normalized with low cost computation. Through a set of experiments, we demonstrate that the use of the proposed system makes it possible to recognize contact less palm images using the conventional palm recognition algorithms.

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

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.

Performance Improvement of Phase-Based Correspondence Matching for Palmprint Recognition

The use of phase-based correspondence matching for biometric recognition makes it possible to find corresponding point pairs between images having nonlinear deformation. On the other hand, the optimal recognition performance cannot be exhibited due to simple approaches for matching score calculation and reference point placement. This paper proposes two techniques to improve performance of phase-based correspondence matching for contactless palmprint recognition. First technique analyzes location of corresponding points and defines a new matching score. Second one selects location of reference points suggested by a Difference of Gaussians (DoG) filter. Through a set of experiments using CASIA contactless palmprint database, we demonstrate that the proposed techniques improve performance of phase-based correspondence matching and exhibit good performance compared with conventional palmprint recognition algorithms.