Improving CBIR systems by integrating semantic features

Nowadays, access to information requires to manage effectively multimedia databases, and among challenges offered to scientific community since last decades, multimedia retrieval techniques (particularly images retrieval) are became an active research direction. Introduced to overcome the main drawbacks encountered by text-based images retrieval, which are the subjective and manual annotation of images, content based images retrieval (CBIR) systems index images according to low-level visual features such as color, texture, shape to retrieve similar images. However, despite the progress achieved in the content based image retrieval, in particular with the relevance feedback approach where the user refine the search via the specification of relevant or not relevant items, the current CBIR systems still have a major difficulty that it has yet to overcome: how to negotiate the "semantic gap"? This problem comes from the mismatch between their capabilities and the needs of users. In this paper, we address the problem of how relate lowlevel features to high level to bring out semantic concepts from images. Our aim is to combine contentbased and metadata-based approaches for image retrieval from a user perspective to yield better results and overcome to the lacks of these techniques when they are taken separately. To represent the semantic content of images, we propose a model which takes account of the interaction between the user and the metadata. In particular, we model the semantic user\´ preference by analyzing its answers through the Relevance Feedback process. Furthermore, we introduce a new machine learning technique that modify the weights (i.e. relative importance) of metadata representing the semantic content of images.