Abstract
With the rapid development of cloud computing technology, more and more users choose to outsource image data to clouds. To protect data's confidentiality, images need to be encrypted before being outsourced to clouds, but this brings difficulties to some basic yet important data services, such as content-based image retrieval. Existing secure image retrieval methods generally have some problems such as low retrieval accuracy and low retrieval efficiency, which cannot meet requirements for large-scale image retrieval in cloud environment. In this paper, we propose a large-scale secure image retrieval method in cloud environment. The Hamming embedding algorithm is utilized to generate binary signatures of image descriptors. A frequency histogram combined with binary signatures is generated to provide a more precise representation of image features in an image and thus the retrieval accuracy is improved. Visual words are selected from the histogram by the random sampling method before the min-Hash algorithm is performed on binary signatures of selected visual words to generate a secure index. The random sampling method and min-Hash algorithm can not only ensure the security of the search index, but also greatly improve the image retrieval efficiency. This method achieves the balance among security, accuracy and efficiency of large-scale secure image retrieval in public clouds. The security analysis and experimental results show the effectiveness of the proposed method.
Highlights
With the popularization of digital cameras and smart phones, multimedia data such as images and videos become much easier to capture and have shown an explosive growth
Xia et al [16] designed a secure retrieval framework based on local features (SIFT), where Earth Mover’s Distance (EMD) is transformed in a way that the cloud service providers (CSP) can evaluate the similarity between images without learning sensitive information
Visual words are selected from the histogram by the random sampling method before the min-Hash algorithm is performed on binary signatures of selected visual words to generate a secure index
Summary
With the popularization of digital cameras and smart phones, multimedia data such as images and videos become much easier to capture and have shown an explosive growth. Xia et al [16] designed a secure retrieval framework based on local features (SIFT), where Earth Mover’s Distance (EMD) is transformed in a way that the CSP can evaluate the similarity between images without learning sensitive information. This method is secure, but two-rounds communication are needed between CSP and users before the CSP obtains top-k ranked images, which is time-consuming and its communication cost is high. This algorithm constructs binary signature vectors for the features assigned to the same clustering center, and a threshold function are used to filter out features that are in the same cluster but have large differences from other features, so that the retrieval accuracy can be improved
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
