Presentation | 2001/3/16 Extraction of Character Strings from Scene Image Based on Feature of Color Contrast Kenji MURAYAMA, Yoshihiro OKADA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose extraction method of character strings from scene image based on feature of color contrast. To understand condition in scene, characters in scene image are the most important information. Especially, important words are intensified by color scheme compared to other words. This effect is said "color contrast". Therefore we use the feature of color contrast to extract important words. Experimental results show that regions which have strong feature of color contrast intend to include important words. And the results show that character strings in scene image are able to extract these regions. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Extraction of Character String / Color Contrast / Scene Image |
Paper # | PRMU2000-227 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2001/3/16(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Extraction of Character Strings from Scene Image Based on Feature of Color Contrast |
Sub Title (in English) | |
Keyword(1) | Extraction of Character String |
Keyword(2) | Color Contrast |
Keyword(3) | Scene Image |
1st Author's Name | Kenji MURAYAMA |
1st Author's Affiliation | Graduate School of Science and Technology, Ryukoku University() |
2nd Author's Name | Yoshihiro OKADA |
2nd Author's Affiliation | Graduate School of Science and Technology, Ryukoku University |
Date | 2001/3/16 |
Paper # | PRMU2000-227 |
Volume (vol) | vol.100 |
Number (no) | 702 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |