Indian Journal of Science and Technology

Abstract

Objectives: Improvement in the retrieval performance of the system can be brought by fusion of image features with different similarity measures. Performance of the system can be further improved by incorporating user’s feedback into the system. Method: An extensive system is proposed based on one of the computational intelligence techniques for the effective retrieval of required images from systems. The proposed technique consists of two main modules, namely: feature vector processing and result enhancement. Feature fusion is performed by application of genetic operators to find the final distance between probe and stored images. Subsequently estimated retrieved images are presented to the user, first k-images will be selected by the user as K-NN query images and are ranked according to their relevance values provided by the user. Optimization of retrieved images is done by iteratively providing user’s feedback to the system. Findings: Feature fusion and effective relevance feedback methods can contribute extensive benefits to content based image retrieval. Feature fusion combines different image features in such a way to get a single feature vector for all of them but combination of different image features however is not always beneficial. Semantic gap is reduced by providing user’s feedback after the retrieval of images. This is an iterative process and it defines a set of relevant images in the end. Genetic algorithm based search is applied for a series of weighting functions which helps to maximize the fitness function. Applications/Improvements: Multifarious features are introduced where different image features are combined with different similarity measures and the final distance is drawn by employing genetic programming technique.
Keywords: Feature Extraction, Image Descriptor, Multifarious Features, Relevance Feedback, Similarity Measure