Yutaka Hirakawa

Learn More
In this paper a new recognition system of distorted patterns is presented, where the Viterbi algorithm and a modified trellis incorporating a pertinent statistics of distorted patterns are used. The system works in a manner quite similar to our own human decision process. The trellis is so constructed that it can eliminate all the irrelevant pattern classes(More)
In auction services such as eBay or yahoo, bidders can select interesting items from among many different items. It takes a long time, however, to investigate various items’ attributes, such as the price, the bids, and the time left. On the other hand, it is possible to circulate large quantities of rich content such as image data by using broadband(More)
User authentication is widely used in many Internet services and is also used by automatic teller machines (ATMs). Recently, there has been an increase in the ATM password thefts using small charge-coupled device cameras. This study discusses a user authentication method in which graphical passwords, instead of alphanumeric ones as, are used to mitigate(More)
User authentication is widely used in automatic teller machines (ATMs) and Internet services. Recently, ATM passwords have been increasingly stolen using small charge-coupled device cameras. This article discusses a user authentication method in which graphical passwords instead of alphabetic ones are used as passwords in order for it to be tolerant to(More)
The authors propose a new face recognition system with an evaluation function using feature points. The feature points are detected automatically by Milborrow’s Stasm software. Before recognition, rotation compensation and size normalization are applied to the feature points. The main method is to calculate the squared error between the registered face and(More)
This paper describes a face recognition algorithm using feature points of face parts, which is classified as a feature-based method. As recognition performance depends on the combination of adopted feature points, we utilize all reliable feature points effectively. From moving video input, well-conditioned face images with a frontal direction and without(More)