Automatic Image Annotation Using a Fuzzy System Based On Color Features

With quick development in digital images and the availability of imaging tools, massive amounts of images are created. Therefore efficient management and suitable retrieval especially by computers is one of the most challenging fields in image processing. Automatic image annotation (AIA) is a process of producing words for a digital image based on the image‘s content. In this paper, we proposed a novel image annotation algorithm using color features in a fuzzy system. For this purpose we used three popular color features including color histogram, color moment, and color Auto-correlogram as a fuzzy system inputs and similarity measure as an output. Experimental results on Corel5k benchmark annotated dataset, demonstrates that using proposed method achieves good performance.

Keywords:

Image annotation , Fuzzy system , Image retrieval , Color features