Preserving privacy while revealing thumbnail for content-based encrypted image retrieval in the cloud

Owing to the rapid development of cloud services and personal privacy requirements, content-based encrypted image retrieval in the cloud has been increasing. Outsourced images are encrypted into noiselike ones to protect privacy, however, the obtained unrecognized appearance limits their availability. Besides, users have to decrypt all search results to browse, while some of them may not be needed, which undoubtedly wastes bandwidth and computing resources. To cope with this problem, a compromise strategy is proposed that considers the tradeoff between privacy and usability of cipher images. Wherein, a thumbnail preserving encryption (TPE) based on genetic algorithm is proposed. The pixels in the sub-blocks of the plain image are scrambled and diffused at the bit-level through crossover and mutation operators of the genetic algorithm. Moreover, two new operators of Mutation Compensation and Mutation Failure are defined and incorporated into the traditional genetic algorithm to achieve an ideal TPE, that cipher image has the same thumbnail as the original image. Additionally, a color histogram-based retrieval algorithm is introduced to retrieve cipher images using the color information preserved by thumbnails; and to improve retrieval accuracy by using the Bhattacharyya distance. A series of simulations verify the security and effectiveness of our scheme.