ot-feature extraction on scrambled images with instantaneous clustering for cbir scheme in cloud computing

A novel feature extraction algorithm using otsu’s threshold (ot-features) onscrambled images and the instantaneous clustering (ic-cbir) approach isproposed for content-based image retrieval in cloud computing. images arestored in the cloud in an encrypted or scrambled form to preserve the privacycontent of the images. the proposed method extracts the features from thescrambled images using the otsu’s threshold. initially, the otsu’s threshold isestimated from the scrambled image and based on this threshold the image isdivided into two classes in the first iteration. again, the new threshold valuesare estimated from two classes. the difference between the new thresholdand the previous threshold gives two features. this process is repeated for lnumber of iteration to obtain the complete ot-features of the scrambled image.this paper also proposes an instantaneous clustering approach (ic-cbir)where the image is moved into a cluster as soon as the image is uploaded bythe image owner. therefore while retrieving the images, the images near to aparticular cluster are matched instead of matching with a complete set of imagefeatures in the dataset which reduces the search time. the performance of theproposed algorithm is being tested using four different types of the datasetsuch as corel 10k, misc, oxford flower, and inria holidays dataset. theexperimental evaluation reveals that the proposed method outperforms betterthan the traditional cbir algorithm on encrypted images in terms of precision,time of search and time of index construction.