Joho Chishiki Gakkaishi

　We propose an individual recognition system using eigenear images. Although face images change owing to changes of emotion, growth, expressions, infirmity, and so on, ear images cannot be affected by them. Our system utilizes principal component analysis for dimensionality reduction, and Mahalanobis' Distance for individual recognition.
　Experimental results show that our system can recognize individuals with the high recognition rate 99.7% - approximately the same rate of an existing method based on Genetic Aleorithm(GA) - in shorter time than that of the GA-based method.

View full abstract

Show abstractHide abstract

　We developed a providing service system of a terminological system, using a framework of Web Services, since we aims at improvement in the reusability and at efficient providing of a terminological system. The following two applications are successfully developed with the providing service system as a back-end service; one is a browsing system of several terminological systems and the other is a cooperating system with Web service of Google: search engine of Web pages. We used EDR technical term dictionary and a hierarchical structure data by Open Directory Project, as typical terminological systems. One service corresponds to one terminological system in our implementation, and has two interfaces; one searches word entries and the other acquires the structure of the entry. Various access methods to a terminological system are integrated to the access method with the framework of Web Service. Then, the method makes it possible for a user and a provider to access a terminological system in distributed way.

View full abstract

Download PDF (1405K)

Register with J-STAGE for free!