Abstract :
Content based image search is gaining utmost importance from the users and researchers due to its user friendly approach. Retrieving the images on the basis of their visual content is itself a remarkable concept. The paper discusses various factors involved in the content based image retrieval and presents the meta-data model for efficient content based image retrieval. This model consists of following improved features i.e. dominant color and relative smoothness and other features like color histogram and edge histogram all together. This model consists of step by step approach to get the maximum relevant results (images) from the database using meta-data. To achieve this, we also include the DWT (Discrete Wavelet Transform) algorithm to give more accurate results.

Keywords :
content based image retrieval; meta-data; color histogram; edge histogram; discrete wavelet transform; correlation heuristic