To provide a document retrieval support apparatus to determine easily whether document data of searching result is desired document data.
The document retrieval support apparatus includes a documentation management section 20 which memorizes the document data; a document string feature management section 19 which memorizes the feature amounts of image data contained in the document data; a page image creating split section 12 which extracts the image data and text data contained in the specified document data; a searching statement part 18 which takes out keywords from the extracted text data and searches the document data containing the keywords out of the document data memorized in the documentation management section 20, while searching the image data similar to the extracted image data by comparing the feature amounts of the extracted image data and the feature amounts of the image data memorized in the document string feature management section 19; and a SG-like image summarization creation section 15 which extracts the image data from the searched document data and generates a stained glass-like image.
| JP2005234772A | 2005-09-02 | |||
| JP2005293576A | 2005-10-20 | |||
| JPH10254892A | 1998-09-25 | |||
| JP2001101207A | 2001-04-13 |
CSNG200400277003; 梅田 恭子 他: '知識メモを活用した研究情報共有方式の提案' 情報処理学会論文誌 Ｖｏｌ．４２，Ｎｏ．１１, 20011115, ＰＰ．２５６２-２５７１．, 情報処理学会