A genetic programming framework for content-based image retrieval

The effectiveness of CBIR systems can be improved by combining image features or by weighting image similarities, as computed from multiple feature vectors. However, feature combination without using similarity functions does not always make sense and the combined similarity function may have to be more complex than weight-based functions in order to satisfy users’ needs. We address this problem by presenting a Genetic Programming framework to the design of combined similarity functions. Our method allows non-linear combination of image similarities and is validated through several experiments, where the images are retrieved based on the shape of their objects. Experiments results demonstrate that the GP framework is suitable to the design of effective combination functions.