A SEMANTIC DESCRIPTION FOR CONTENT-BASED IMAGE RETRIEVAL
Robust and flexible semantic labeling of images is still a basic problem in content-based image representation and retrieval. In this paper, a self-organizing image description model (SID) was put forward for describing the image high-level semantic content. This model is a hierarchical architecture, which includes primitive image layer, image feature layer, image semantic layer, multi-level semantic pattern layer and semantic labeling layer. A semantic-based retrieval algorithm (SBRA) for image high-level semantic content retrieval was designed and implemented. The performance of an experimental image retrieval system is evaluated on a database of around 3000 images. The experimental results show that SID and SBRA are effective in describing image high-level semantic content and can provide flexible image description and efficient image retrieval performance.
Content-based image retrieval Image semantic model Semantic description Image clusters SVM
BING WANG XIN ZHANG XIAO-YAN ZHAO ZHI-DE ZHANG HONG-XIA ZHANG
College of Mathematics and Computer Science, Hebei University, Baoding 071002, China College of Electronics and Information Engineering of Hebei University, Baoding, 071002, China Department of Information Management and Engineering of Hebei College of Finance, Baoding, 071051, C
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
2466-2469
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）