1 0 0 0 自己組織化情報ベース機能領域(<特集>「RWC-実世界知能」)
- 著者
- 岡 隆一 橋田 浩一 Ryuichi Oka Koichi Hasida
- 出版者
- 一般社団法人 人工知能学会
- 雑誌
- 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
- 巻号頁・発行日
- vol.17, no.2, pp.153-162, 2002-03-01
- 参考文献数
- 39
- 被引用文献数
- 1
1 0 0 0 OA 自己組織化情報ベース機能領域(<特集>「RWC-実世界知能」)
- 著者
- 岡 隆一 橋田 浩一 Ryuichi Oka Koichi Hasida
- 雑誌
- 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
- 巻号頁・発行日
- vol.17, no.2, pp.153-162, 2002-03-01
- 著者
- Yuichi Yaguchi Kenta Iseki Ryuichi Oka
- 出版者
- Information Processing Society of Japan
- 雑誌
- IPSJ Transactions on Computer Vision and Applications (ISSN:18826695)
- 巻号頁・発行日
- vol.2, pp.1-14, 2010 (Released:2010-02-04)
- 参考文献数
- 39
- 被引用文献数
- 1 5
A two-dimensional continuous dynamic programming (2DCDP) method is proposed for two-dimensional (2D) spotting recognition of images. Spotting recognition is the simultaneous segmentation and recognition of an image by optimal pixel matching between a reference image and an input image. The proposed method performs optimal pixel-wise image matching and 2D pixel alignment, which are not available in conventional algorithms. Experimental results show that 2DCDP precisely matches the pixels of nonlinearly deformed images.