Abstract Firstly, a fully unsupervised segmentation algorithm with improved k-means is employed to divide images into regions. Then, a method of information bottleneck is proposed to cluster the segmented region and the relationship between image semantic concept and clustering regions is established. Image segmentation is used in the unannotated image so that the conditional probability of each semantic concept can be calculated under the condition of segmenting region. The image semantics is automatically annotated by keywords with maximal conditional probability. The system is implemented and tested on a 500-image database, and the experimental results show that the effectiveness of the proposed method outperforms others.
[1] Zhong Hong, Xia Limin. Ontology-Based Image Retrieval. Computer Engineering and Applications, 2007, 43(17): 37-40 (in Chinese) (钟 洪,夏利民.基于本体的图像检索.计算机工程与应用, 2007, 43(17): 37-41) [2] Ouyang Junlin, Xia Limin. Image Retrieval Based on Color and Shape Features. Journal of Chinese Computer Systems, 2007, 28(7): 1262-1266 (in Chinese) (欧阳军林,夏利民.基于二值信息的颜色和形状特征的图像检索.小型微型计算机系统, 2007, 28(7): 1262-1266) [3] Wang Lei, Liu Li, Latifu K. Automatic Image Annotation and Retrieval Using Subspace Clustering Algorithm // Proc of the 2nd ACM International Workshop on Multimedia Databases. Washington, USA, 2004: 100-108 [4] Duygulu P, Barnard K, de Freitas N. Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary // Proc of the 7th European Conference on Computer Vision. Compehagen, Denmark, 2002, Ⅳ: 97-112 [5] Li Wei ,Sun Maosong. Automatic Image Annotation Based on WordNet and Hierarchical Ensembles. // Proc of the 7th International Conference on Computational Linguistics and Intelligent Text Processing. Mexico City, Mexico, 2006: 417-428 [6] Lu Jing, Ma Shaoping. Automatic Image Annotation Based on Concept Indexing. Journal of Computer Research and Development, 2007, 44(3): 452-459 (in Chinese) (路 晶,马少平.基于概念索引的图像自动标注.计算机研究与发展, 2007, 44(3): 452-459) [7] Slonim N, Tishby N. Agglomerative Information Bottleneck // Solla S A, Leen T K, Müller K R, et al. Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 1999: 617-623 [8] Jain R, Kasturi R, Schunck B G. Machine Vision. New York, USA: Mc-Graw Hill, 1995 [9] Wagstaff K, Cardie C, Rogers S, et al. Constrained k-Means Clustering with Background Knowledge // Proc of the 18th International Conference on Machine Learning. Williams College, USA, 2001: 577-584 [10] Yang M H, Ahuja N, Gaussian Mixture Model for Human Skin Color and Its Application in Image and Video Database // Proc of the SPIE Conference on Storage and Retrieval for Image and Video Databases. San Jose, USA, 1999: 458-466 [11] Wang Lei, Khan L. Automatic Image Annotation and Retrieval Using Weighted Feature Selection. Multimedia Tools and Applications, 2006, 29(1): 55-71 [12] Jeon J, Lavrenko V, Manmatha R. Automatic Image Annotation and Retrieval Using Cross-Media Relevance Models // Proc of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Toronto, Canada, 2003: 119-126
2008, Vol. 21 
