Image retrieval based on data hiding

With the wide spread of internet, image databases with large amount of information are used in various applications such as product briefing, personal information provider, and so on. These image databases show some difficulty in retrieving the information in real-time whereas other databases using the text information are retrieved relatively fast. In this paper, image retrieval method is proposed, in which the image is extracted using the hidden text information related to it. By invisible modification of images, the images are retrieved without any headers or separate files linked to them. This paper presents the robust data hiding method by separating the image into the edge and non-edge regions. The sum of the 8x8 image block is quantized by adding the pseudo noise depending on the data bit. The amount of the pseudo noise is controlled adaptively based on the gradient magnitude of the image block. Real-time extraction of extra data by the proposed algorithm is desirable for the practical image retrieval system. Experiments with various test image sets show that the proposed data embedding algorithm is robust to joint photographic experts group (JPEG) compression.