Cross-Language Peculiar Image Search Using Translaion between Japanese and English
As next steps of Image Retrieval, it is very important to discriminate between “Typical Images” and “Peculiar Images” in the acceptable images, and moreover, to collect many different kinds of peculiar images exhaustively. As a solution to the 1st next step, my previous work has proposed a novel method to more precisely search the Web for peculiar images of a target object by its peculiar appearance descriptions (e.g., color-names) extracted from the Web and/or its peculiar image features (e.g., color-features) converted from them. This paper proposes a refined method equipped with cross-language (translation between Japanese and English) functions and validates its retrieval precision.
KeywordsTarget Object Image Retrieval Original Query Acceptable Image Text Mining Technique
Unable to display preview. Download preview PDF.
- 1.Hattori, S., Tanaka, K.: Search the Web for typical images based on extracting color-names from the Web and converting them to color-features. Letters of DBSJ (Database Society of Japan) 6(4), 9–12 (2008)Google Scholar
- 2.Hattori, S., Tanaka, K.: Search the Web for peculiar images by converting Web-extracted peculiar color-Names into color-features. IPSJ (Information Processing Society of Japan) Transactions on Databases 3(1), 49–63 (2010)Google Scholar
- 3.Hattori, S.: Peculiar image search by Web-extracted appearance descriptions. In: Proceedings of the 2nd International Conference on Soft Computing and Pattern Recognition (SoCPaR 2010), pp. 127–132 (2010)Google Scholar
- 4.Hattori, S., Tezuka, T., Tanaka, K.: Extracting visual descriptions of geographic features from the Web as the linguistic alternatives to their images in digital documents. IPSJ Transactions on Databases 48(SIG11), 69–82 (2007)Google Scholar
- 6.Wikipedia - List of colors, http://en.wikipedia.org/wiki/List_of_colors
- 7.Japanese Industrial Standards Committee. Names of Non-Luminous Object Colours. JIS Z 8102:2001 (2001)Google Scholar
- 8.Smith, J.R., Chang, S.-F.: VisualSEEk: A fully automated content-based image query system. In: Proceedings of the 4th ACM International Conference on Multimedia (ACM Multimedia 1996), pp. 87–98 (1996)Google Scholar