作者： Seong-Yong Hong
DOI:
关键词: Computer science 、 Computer vision 、 Image texture 、 Automatic image annotation 、 Artificial intelligence 、 Focus (optics) 、 Information retrieval 、 Visual Word 、 Similarity (psychology) 、 Color image 、 Search engine indexing 、 Image retrieval
摘要: Most of the content-based image retrieval systems focus on similarity-based images by utilizing color, shape and texture features. In this paper we propose a new searching scheme, called FMV Indexing, to guarantee higher quality. This scheme allows us retrieve based high-level semantic concepts such as “cool,” “soft,” “strong,” etc. Our experimental results show that proposed techniques can facilitate users’ intentions more accurately give favorable feeling satisfaction users.