An Image Security Retrieval Method Based on Homomorphic Encryption

Abstract

The invention relates to an image security retrieval method based on homomorphic encryption. Firstly, the color, texture, shape and other features of the image are extracted, and the dimensionality of the image features is reduced by using the LPP method; then the features are protected by using the Paillier homomorphic encryption algorithm; finally, the similarity matching is directly performed on the encrypted image features, and the most similar The K images are fed back to the user as retrieval results. The present invention is based on the CBIR framework, adopts the homomorphic encryption technology, does not need to decrypt, but uses the homomorphic characteristic of the Paillier encryption algorithm to directly measure the similarity of the encrypted image features. The invention overcomes the deficiency that the existing image retrieval method cannot directly retrieve the encrypted image. Experimental results show that the present invention can obtain retrieval results completely consistent with the original plaintext domain CBIR method on the premise of ensuring the security of image information, and encryption will not affect the retrieval performance of images.

Description

technical field [0001] The invention belongs to the field of multimedia information security, in particular to an image security retrieval method based on homomorphic encryption. Background technique [0002] With the continuous development of cloud computing technology, cloud computing has been gradually applied in entertainment, electric power, transportation, energy and other fields. These industry sectors provide users with various services through cloud computing. Cloud storage is one of the infrastructures of cloud computing. Massive image data is often stored in cloud storage. These image data often contain a large amount of user privacy information. However, the existing cloud storage mechanism does not provide users with Security protection mechanism, the leakage of these private information will cause serious consequences. Issues such as cloud computing security and privacy protection have gradually become key issues that hinder the wider application of cloud com...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem in the prior art that when retrieving an encrypted image, it must first be decrypted and then retrieved, so that the security of user information cannot be truly guaranteed. The present invention proposes an image security retrieval method based on Paillier homomorphic encryption, which encrypts image features. Homomorphic encryption technology allows users to directly calculate and compare encrypted data, so that the encrypted image features can be retrieved without decryption, which can ensure the security of the image without affecting the retrieval performance of the image

Images