Content based image retrieval using color histogram

With the availability of easy and inexpensive methods to create and store images in digital formats, the visual information preserved and shared electronically has grown dramatically. Since the non-textual information like images, audio and video preserved in digital format are increasing day by day, effective applications to manage and retrieve these content are essential, which are commonly known as content based image retrieval (CBIR). Firstly, keyword annotation is labor intensive, and it is not even possible when large sets of images are to be indexed. Secondly, these annotations are drawn from a predefined set of keywords which cannot cover all possible concepts images may represent. Finally, keywords assignment is subjective to the person making it. This paper focuses on color based image retrieval to develop a system that uses the color as a visual feature to represent the images. To improve the efficiency and effectiveness of color-based retrieval, color histogram method has been proposed. Experimental results show that the color histogram features containing spatial structural relations are robust to image translation, scaling and rotation, and for retrieval of visually similar object from the image sequences, the color histogram method gives good retrieval precision with speed.