文章基本信息

标题：誘目性に寄与する物理的特徴量を基にした画像注目領域の抽出
本地全文：下载
作者：田中昭二 ; 井上正之 ; 井上誠喜等
期刊名称：映像情報メディア学会誌
印刷版ISSN：1342-6907
电子版ISSN：1881-6908
出版年度：1998
卷号：52
期号：6
页码：881-890
DOI：10.3169/itej.52.881
出版社：The Institute of Image Information and Television Engineers
摘要：A viewer usually does not perceive everything in a picture. The objects in the picture that the viewer perceives depend on the structures in the view, the meanings of the objects, the mental condition of the viewer, and so on. If it is assumed that the impressions of the viewer are determined by what objects he or she pays attention to, highly attractive regions of a picture would have a lot of information that contribute to the impressions. Consequently, it is important to analyze those attractive regions for human impression prediction. This paper proposes a method for extracting attractive regions from pictures. This method evaluates the attractiveness of each segmented region. For the evaluation, we defined an evaluation function based on hue, saturation, lightness, and size of the region, as well as, color difference between the region and its surroundings. In our experiments, the proposed method could precisely extract attractive regions.
关键词：感性;誘目性;領域分割