出版社:International Association for Computer Information Systems
摘要:Most of the content-based image retrieval systems focus on similarity-based retrieval of images by utilizing color, shape and texture features. In this paper we propose a new searching scheme, called FMV Indexing, to guarantee higher retrieval quality. This scheme allows us to retrieve images based on high-level semantic concepts such as “cool,” “soft,” “strong,” etc. Our experimental results show that proposed techniques can facilitate users’ searching intentions more accurately and give a more favorable feeling of satisfaction to users.
关键词:FMV Indexing; Human Sensation and;Emotion; Color Image Retrieval System