Heuristic and Intermediate Features Based Image Retrieval

In this paper, a new method for heuristics and intermediate features based image retrieval is proposed. Heuristic features are identified and directly stored into the database and easily retrieved also. An algorithm is used to convert low level features hue, saturation and intensity in HSI space to semantic based color names. Images can be retrieved by these semantic color names. For semantics based texture queries, statistical values of textures calculated from the image are used as the low level features in image retrieval. But these low level features are mostly not understandable by the general human. There is always a semantic gap between human understanding and low level features. Image database is constructed with low level texture features obtained from Gray Level Co-Occurrence 1732 Dipankar Hazra et al. Matrix (GLCM). Semantic level queries from the user mapped to the low level features at retrieval time to retrieve the required images.