An Innovative Method for Retrieving Relevant Images by Getting the Top-ranked Images First Using Interactive Genetic Algorithm

The prime goal of the CBIR system is to construct meaningful descriptions of physical attributes from images. Physical features and mathematical features are two such typical descriptions. Many research efforts have been made to extract physical features such as color, texture, edge, structure or a combination of two or more. The majority of the proposed solutions are variations of the color histogram initially proposed for object recognition. Since color histogram lacked spatial information these methods were liable to produce false positives especially when the database was large. We proposed a method called image retrieval using interactive genetic algorithm (IRIGA) for computing a very large number of highly selective features and comparing these features for some relevant images and using only those selected features which capture similarity in the given relevant images for image retrieval. Experiments on a collection of 10 000 general-purpose images demonstrate the effectiveness of the proposed framework.