Probability Association Approach in Automatic Image Annotation

introduction Content-based image retrieval (CBIR) has wide applications in public life. Either from a static image database or from the Web, one can search for a specific image, generally browse to make an interactive choice, and search for a picture to go with a broad story or to illustrate a document. Although CBIR has been well studied, it is still a challenging problem to search for images from a large image database because of the well-acknowledged semantic gap between low-level features and high-level semantic concepts. An alternative solution is to use keyword-based approaches, which usually associate images with keywords by either manually labeling or automatically extracting surrounding text from Web pages. Although such a solution is widely adopted by most existing commercial image search engines, it is not perfect. First, manual annotation, though precise, is expensive and difficult to extend to large-scale databases. Second, automatically extracted surrounding text might by incomplete and ambiguous in describing images, and even more, surrounding text may not be available in some applications. To overcome these problems, automated image annotation is considered as a promising approach in understanding and describing the content of images. Automatic image annotation is derived from the manual annotation for CBIR. Since the semantic gap degrades the results of image search, the text descriptions are considered. It is desired that the text and the visual features cooperate to drive more effective search. The text labels, as the high-level features, and the visual features, Probability Association Approach in Automatic Image Annotation as the low-level features, are complementary for image content description. Therefore, automatic image annotation becomes an important research issue in image retrieval. In this chapter, some approaches for automatic image annotation will be reviewed and one of the typical approaches is described in detail. Then keyword-based image retrieval is introduced. The general applications of automatic image annotation are summarized and explained by figure examples.