A multi-intelligent terminal shared face secret recognition method based on cloud environment

Abstract

The cloud-based multi-smart terminal shared face concealment recognition method proposed by the present invention can be performed under a safe protocol, and at the same time can simultaneously protect the privacy of user image data and the privacy of a third-party face detector. The present invention applies the secure inner product algorithm to secure face detection in the cloud environment for the first time, which not only realizes the ciphertext storage of user images, but also provides the function of querying the required images in the ciphertext state, and also ensures that third parties The face detector is not leaked. In addition, since the form of user image storage is encrypted with a standard encryption algorithm, the reliability of data security can be guaranteed, and the secure inner product algorithm is used for each query, and the complexity of the algorithm is related to the selected encryption matrix dimension. The complexity is low and can be flexibly configured according to computing power and security requirements. The amount of local calculation is small, and a large number of calculations are processed by the cloud with powerful computing power, which effectively shortens the detection time. And the encryption method is easy to realize by software, and the present invention can be widely applied to cloud computing, face recognition and the like.

Description

technical field

[0001] The invention belongs to the fields of cryptography and computer vision, in particular to a method for concealed face detection and recognition, in particular to a cloud environment-based multi-smart terminal shared face concealed recognition method. Background technique

[0002] In the era of mobile Internet, a surge of mobile users backs up their photos to cloud servers. When a huge number of images are stored on the cloud server, the privacy of users becomes an issue that cannot be ignored, for example, the face information of family members, the possible relationship between people, the geographic location where the photo was taken, home address, work unit, school, etc. etc. will be exposed to unknown dangerous people, threatening personal and property safety. So images should be stored in ciphertext rather than plaintext. At the same time, the face detector used in the face image retrieval service provided by the cloud server is also provided by...

Images