An effective hybrid framework for content based image retrieval (CBIR)

In recent years, we have witnessed a massive growth in the generation of images on the cyberspace which demands to develop automated solutions for effective content management. Content-based image retrieval (CBIR) systems have been proposed to reduce the dependency on textual annotations-based image retrieval systems. There exists a variety of features-classifier combinations based CBIR methods to analyze the content of query image for relevant images retrieval. Although, these methods provide better retrieval performance in single-class scenario, however, we experience a significant performance drop in multi-class search environments due to semantics similarity among the images of different classes. CBIR methods based on the hybrid classification model offer better retrieval accuracy, however, we experience a biased classification towards the negative class due to the class imbalance problem when we experience an increase in the number of negative samples due to highly correlated semantic classes. Thus, multiple classifiers based CBIR models become unstable especially in one-against-all classification settings. To address the aforementioned problem, we proposed a CBIR method based on a hybrid features descriptor with the genetic algorithm (GA) and SVM classifier for image retrieval in multi-class scenario. More specifically, we employed the first three color moments, Haar Wavelet, Daubechies Wavelet and Bi-Orthogonal wavelets for features extraction, refine the features using GA and then train the multi-class SVM using one-against-all approach. L-2 Norm is used as a similarity measurement function between the query image and retrieved images against the query image from the image repository. The proposed technique successfully addresses the class imbalance problem in CBIR. Performance of the proposed method is evaluated on four standard datasets i.e. WANG, Oxford Flower, CIFAR-10, and kvasir and compared with 25 different CBIR methods. Experimental results illustrate that our method outperforms the existing state-of-the-art CBIR methods in terms of image retrieval.