Secure and efficient image retrieval through invariant features selection in insecure cloud environments

Advances in computer vision technologies lead to a renewed focus on content-based image retrieval (CBIR) in computer multimedia content analysis applications. CBIR is a technique for image retrieval using automatically derived features. As the size of image repositories grew, supported by increased cloud storage adoption, security concern around trust in cloud service provider (CSP) witnessed a resurgence of interest in user privacy. Hence, unlike in traditional CBIR, cloud-based image retrieval is based on the encrypted feature vector. This may reduce the overall retrieval performance of the system. Consequently, mechanisms are needed to protect the feature vector and the actual images during transmission. Second, to provide image content security, images are often encrypted by users before uploading to the cloud. This article addresses the challenges of retrieving images securely from an untrusted cloud environment. Images are represented in terms of their local invariant features to form an image feature vector. Later, an asymmetric scalar-product-preserving encryption (ASPE) is applied to secure the feature vector. Then, images are encrypted before they are uploaded to a cloud server. The proposed method has been tested on various Corel image datasets and the medical image repository. Performance evaluation shows that the proposed method outperforms its best secure CBIR systems in the literature.