A fast image-gathering system from the World-Wide Web using a PC cluster

摘要

Due to the recent explosive progress of WWW (World-Wide Web), we can easily access a large number of images on WWW. There are, however, no established methods to make use of WWW as a large image database. In this paper, we describe an automatic image-gathering system from WWW, in which we use both keywords and image features. By exploiting some existing keyword-based search engines and selecting images by their image features, our system obtains, with high accuracy, images that are relevant to query keywords. Our system has the following two novel properties: (1) It does not need to make a huge index for a great number of images on the whole WWW because of taking advantage of commercial keyword-based text-search engines. (2) It can gather a lot of images related to given keywords full-automatically without a user's intervention during the processing. The system has been implemented on a parallel PC cluster, which enables us to gather more than one hundred images from WWW in about one minute.