One of multimedia content acquisition method on the Web is using tag which is describe of content. However, different words may be tagged to the same or similar subjects, because tagging is performed in an essentially arbitrary manner by a human. In addition, tags are provided in specific language from the content. This model proposes the method of automatically tagging which compensate insufficient described content by using multilanguage. Our experimental evaluations showed that users could obtain more appropriate images with this method.
展开▼
