期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2008
卷号：8
期号：1
页码：170-178
出版社：International Journal of Computer Science and Network Security
摘要：Image classification is one disposal procedure for high level semantic analysis, e.g., image data mining, knowledge discovery and intelligent data analysis. As one image generally contains multiple semantic objects, it��s not appropriate to conduct image classification according the global features. So, image segmentation is a must before image classification. However, accurate semantic segmentation is still out of implicit semantic object regions in one image, as one semantic object with distinct regions would be segmented into several irrelevant regions by current most image segmentation algorithms based low level color or texture features, i.e., the hierarchical clustering based approach (HCBA), the eigenregions based strategy (EBS), and the novel region based methods (NRBM). This leads to the effectivity lose for these region-based image classification schemes, as a larger number of implicit regions will be achieved. Meanwhile, these individual regions are generally meaningful and unexpected results would be caused by these classification strategies, although some salient regions are extracted to reduce the complexity of region-based image classifications. Furthermore, these schemes are the arbitrary classification schemes, and could not indicate the information about other implicit objects. In this paper, we proposed salient region based fuzzy classification (SrFC) methods. Firstly, we give a salient region extraction algorithm based dominant colors and Gabor texture features. Then, according to the proposed classification scheme the salient regions from all the candidate images are clustered into disjoint categories. These categories are further used as for those for candidate images, and for each candidate image its number of salient regions belonging to the same category would be used to evaluate the degree of the images belonging to the category. Experiments showed the propose SrFC scheme can achieve better performance than that of current common schemes. With comparison to the HCBA scheme for individual salient regions, the classification accuracy is improved about 16% by the proposed SrFC scheme.
Loading...
