Atsushi Hiroike

Learn More
We have developed a visualization method and an interface for image retrieval. In our method, principal component analysis is dynamically applied to the retrieved images in order to determine their eigenspace and the retrieved images are displayed in that space. We also experimentally evaluated our method from a statistical point of view. And we found that(More)
In a retrieval system for vast amounts of image data, the primary storage cannot hold all image feature vectors because a huge data capacity would be required. Therefore, it is necessary to handle a slow-access secondary storage effectively as well as a first-access primary storage. In this paper, we propose a data-alignment optimization method in the(More)
We have developed a similarity-based image retrieval system that represents retrieved images as a scatter diagram in a semantic space. An axis of the space shows the suitabilities of a keyword assigned to the images. The suitabilities are estimated by a linear transformation of the image features of retrieved data, and the coefficients of the transformation(More)
We have developed a prototype system with image discrimination for the filtering and rating of web pages displaying inappropriate content. We used the SafetyOnline rating standard for the system. The rating standard defines five categories having five levels. The system rates web pages and classifies them into five levels of inappropriateness for each(More)
  • 1