Nobuyuki Nishiuchi

Biometric verification using the motion of fingers: a combination of physical and behavioural biometrics

Although verification using traditional behavioural biometrics provides many advantages, this approach is often inaccurate owing to a lack of repeatability. We, therefore, propose a new method of biometric verification using one of the most repeated motions of the body: the bending motion of fingers. The proposed verification method combined both physical and behavioural biometrics in an attempt to differentiate individuals based on temporal continuity and static profiles. In the algorithm, curvature profiles (biological data) and finger joint angles (dynamic data) were calculated from the binary image edge pixels of the forefinger. In the comparison step, the biological data were compared only when the dynamic data of the probe data were consistent with the reference data. On the basis of our validation, we confirmed the repeatability of the bending motion of the finger, and demonstrated that our proposed method is sufficiently accurate for the initial validation of this biometric verification system.

Hybrid fingerprint authentication using artifact-metrics

Fingerprint authentication has been the latest technology available for personal identification. However, it has a major problem of spoofing. In this paper, the authors propose an anti-spoofing method that is a hybrid fingerprint authentication using artifact-metrics. The artifact-metrics is a coined word, and is technology that authenticates an artifact using a peculiar feature of objects. In this research, a round sticker that has a random pattern is used as the artifact, and is put on the fingernail of the same finger which fingerprint has been used. In this method, three verifications are done. The first verification is the fingerprint, the second is the artifact, and the third is the relation between the fingerprint and the artifact. If the information of fingerprint and the artifact are stolen, the spoofing can be prevented by the third verification, the relation between the fingerprint and the artifact.

Cancelable Biometric Identification by Combining Biological Data with Artifacts

Recently, due to the ability to accurately and rapidly identify an individual using physical attributes, the development of identification systems using biometrics has attracted a great deal of interest. Despite progress with various types of systems, users are often hesitant to submit their unique biological data during the initial enrollment process. In addition, current biometric identification systems have a major vulnerability: spoofing. In this study, we introduce a novel method of cancelable biometric identification that combines biological data with the use of artifacts, and is resistant to spoofing.

A Study of Visibility Evaluation for the Combination of Character Color and Background Color on a Web Page

A design guide for the combination of character color and background color on a Web page has not been researched specifically. Previous research only investigated a limited number of color contrast combination. However, through this research subjects are able to see a huge number of combinations.We developed the color combinations system that continuously changed hue, chroma, and brightness of the character color and the background color. Subjects are able to operate the scrollbar to change the character colors and the background colors continuously. Using this system, we evaluated the visibility of the character on the Web page through the experiments. We get the experiment results that the best coloration is the background color in the cold hue group and the character color in the warm hue group.

A Biometric Identification Using the Motion of Fingers

We propose a new method of biometric identification using the bending motion of fingers that is one of the highest repeated motions of the body. Forefingers consist of hinge joints that enable them to move in one direction only. They also have a tendon that helps the first joint of the finger move in tandem with the second joint. It causes high repeatability. In the algorithm, curvature, one of the behavioral profiles, is calculated from the edge pixels of binary image of the forefinger. Joint angle of the forefinger is measured, and the behavioral profiles are compared only when the joint angle of compared data is consistent with registered data. Proposed behavioral biometrics is able to define the comparison based on temporal continuity and static profiles providing high accuracy. From the experimental results, it is learned that this much data is sufficiently accurate for the identification.

Objective Evaluation Method of Usability Using Parameters of User’s Fingertip Movement

The subjective evaluation method of usability is costly and time-consuming, and is sometimes more unreliable data than objective evaluation method because of the subjective view. On the other hand, the objective evaluation method is traditionally useful and reliable, but expensive. Further, this method is often not feasible, as acquiring the operation logs of many electrical products can be difficult. To overcome current limitations, we propose an objective evaluation method of usability that is applicable to various types of interfaces, such as those of actual electrical products or reproduced interfaces on a touch screen. Our proposed method involves extracting recorded fingertip movements of users during operation via image processing and then evaluating usability based on measurable parameters. Experimental results demonstrate that the proposed method was able to identify problems with usability even when the traditional objective evaluation method could not.

Development of a Usability Evaluation Method Based on Finger Movement

Current techniques for usability evaluation are costly, time-consuming, subjective, and often require operation logs, which are difficult to obtain from electrical products. To overcome these limitations, we developed a usability evaluation method that is applicable for various types of interfaces and involves extracting the video-recorded fingertip movements of a user during operation through image processing, and then evaluating usability based on several measurable parameters. Specifically, users’ hand movements are first video recorded during the operation of either an actual product or a reproduced interface on a touch screen, and then operation time, and the distance and patterns of the moving locus, including stationary time and frequency of directional changes, are then extracted using image processing. To evaluate the usability of the interface, the ratio between novice and expert users for the parameters of operation time and distance traveled by the moving locus is used. Here, we conducted a comparative usability experiment using facsimile interfaces of two different manufacturers to evaluate the performance our method.

Branching Probabilities Planning of Stochastic Network for Project Duration Planning

Projects such as new product development have the similar uncertainty about the job sequence/duration of the project. In order to complete the project by the desired date with a certain confidence, the variable times or branching probabilities should be designed appropriately. In this paper, we will propose a new planning method for the branching probabilities to realize the desired project duration. We usually represent project processes as stochastic networks, such as GERT. In realistic projects, we must analyze generalized complex GERT networks. In this case, analytical treatment is difficult because of the network complexity. Monte Carlo simulation is a practical technique for complex GERT networks. The project duration is determined based on the variable-time and the branching-probability for each arrow. By our former method, we can estimate the project duration efficiently by analyzing the times and probabilities by the combination use of Monte Carlo simulation and probability theory. However, the reverse problems are difficult to be solved; that is, it is difficult for us to find branching probabilities that can realize the desired project duration. We propose a planning method for branching probabilities to realize the desired project duration using genetic algorithm technique supported by Monte Carlo simulation. By our method, we can plan the set of branching-probabilities to finish the project by the desired date. Also, we can show the sensitivity of each arrow for the better project management.

New structured and hierarchical network model for designing FA control system

This paper proposes a new method for FA system software development. As computer technology continues to be upgraded yearly to higher levels, factory automation systems are becoming larger and more complex. The system architecture has changed from centralized processing to distributed processing to reduce the development cost and improve reliability. When we develop distributed processing systems, sometimes we encounter difficulties; for instance, inadequate expression methods, and not yet established analyzing techniques for the control mechanism. These difficulties are derived from non-deterministic characteristics of FA systems, and there are a large number of combinations of control conditions based on the characteristics. Our research proposes a new development method for FA system software to solve the above problems. The main idea behind our method is to delineate the total control logic in a structured and hierarchical network model. We have also developed a software engineering system based on the proposed method.

Study on behavioral biometrics to predict user's interest level using web access log

The value of the users access log in the website has been improved tremendously. Moreover, web analytics service has been widely used, and the web analytics has become commonly effective. The objective of this study is to propose the behavioral biometrics to predict the users interest level in a specific product using access log of websites. We conducted the experiment in which the subjects were asked to perform the shopping task on websites. The comparative analysis is conducted between the interest level of one category product getting through the interview and the access log during the purchasing process in websites. The results show that the behavioral patterns of the web searching and some parameters based on the access log were clearly different depending on the interest level.