講演名 2006/1/3
SKETCH-BASED FINE-TUNING OF IMAGE SEGMENTATION METHODS(International Workshop on Advanced Image Technology 2006)
,
PDFダウンロードページ PDFダウンロードページへ
抄録(和)
抄録(英) A method for evaluating image segmentation methods is proposed in this paper. The method is based on a perception model where the drawing act is used to represent visual mental percepts. Each segmented image is represented by a minimal set of features and the segmentation method is tested against a groundtruth database of sketches that represent the original images, using the Mahalanobis distance function. The covariance matrix is set using a collection of sketches drawn by different users. This evaluation method can be used to solve the problem of parameter selection in image segmentation, as well as to show the goodness or limitations of the different segmentation algorithms. Different well-known color segmentation algorithms are analyzed with the proposed method and the nature of each one is discussed. This evaluation method is also compared with heuristic functions that serve for the same purpose, showing the importance of using users' pictorial knowledge.
キーワード(和)
キーワード(英)
資料番号 IE2005-202
発行日

研究会情報
研究会 IE
開催期間 2006/1/3(から1日開催)
開催地(和)
開催地(英)
テーマ(和)
テーマ(英)
委員長氏名(和)
委員長氏名(英)
副委員長氏名(和)
副委員長氏名(英)
幹事氏名(和)
幹事氏名(英)
幹事補佐氏名(和)
幹事補佐氏名(英)

講演論文情報詳細
申込み研究会 Image Engineering (IE)
本文の言語 ENG
タイトル(和)
サブタイトル(和)
タイトル(英) SKETCH-BASED FINE-TUNING OF IMAGE SEGMENTATION METHODS(International Workshop on Advanced Image Technology 2006)
サブタイトル(和)
キーワード(1)(和/英)
第 1 著者 氏名(和/英) / David GAVILAN
第 1 著者 所属(和/英)
Graduate School of Information Science & Engineering, Tokyo Institute of Technology
発表年月日 2006/1/3
資料番号 IE2005-202
巻番号(vol) vol.105
号番号(no) 501
ページ範囲 pp.-
ページ数 6
発行日