Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

カテゴリ: 全国大会

論文No: 3-056

グループ名: 【全国大会】平成23年電気学会全国大会論文集

発行日: 2011/03/05

タイトル(英語): Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

著者名: 韓 先花(立命館大学),陳 延偉(立命館大学)

著者名(英語): Xian-Hua Han(Ritsumeikan University),Yenn-Wei Chen(Ritsumeikan University)

キーワード: Modality classification|Visual features|feature fusion|kernel function|Bao-of-Feature|Textual feature

要約(日本語): In this paper, we describe an approach for the automatic modality clas- sification in medical image retrieval task of the 2010 CLEF cross-language image retrieval campaign (ImageCLEF). This work is focused on the process of feature extraction from medical images and fusion the different extracted visual feature and textual feature for modality classification. To extract visual features from the images, we used histogram descriptor of edge, gray or color intensity and block-based variation as global features and SIFT histogram as local feature, and the binary histogram of some predefined vocabulary words for image captions is used for textual feature. Then we combine the different features using normalized kernel functions for SVM classification. The proposed algorithm is evaluated by the provided modality dataset by ImageCLEF2010.

原稿種別: 日本語

PDFファイルサイズ: 2,048 Kバイト