Multi-source encrypted image retrieval method supporting privacy protection

A technology for encrypting images and protecting privacy. It is used in special data processing applications, instruments, and electrical digital data processing, and can solve problems such as image similarity information leakage.

Active Publication Date: 2018-07-06
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the method, a new image similarity measurement method is proposed, which solves the problem of image similarity information leakage on the cloud server.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-source encrypted image retrieval method supporting privacy protection
  • Multi-source encrypted image retrieval method supporting privacy protection
  • Multi-source encrypted image retrieval method supporting privacy protection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] This embodiment describes the system model during the implementation of a privacy-protected multi-source encrypted image retrieval method of the present invention, such as figure 1 shown.

[0062] From figure 1It can be seen that there are multiple image owners, and they respectively outsource the encrypted image set and encrypted image feature set to cloud services for storage and retrieval, and at the same time they will send the image encryption key to KMC for storage through a secure channel; The authorized user will submit an encrypted query to the cloud service, and decrypt the encrypted result set ReCRes returned by the cloud service to obtain the original result set Res. At the same time, the authorized user will send the encrypted image key of this query to KMC; in order to improve the retrieval efficiency, the cloud service will establish a retrieval index based on the encrypted image data outsourced by the image owners. To further protect the privacy inform...

Embodiment 2

[0066] This embodiment describes the image similarity and image retrieval results during the implementation of a multi-source encrypted image retrieval method supporting privacy protection described in the present invention, such as Figure 4 and Figure 5 shown.

[0067] Figure 4 is the percentage of real similar images in the corresponding position range of the result set; Figure 5 is the F1 index of the search result.

[0068] Such as Figure 4 As shown, when using Euclidean distance to measure image similarity, the proportion of real similar images distributed in the first 10% is very large, and along with the increase of the result set range, the distribution percentage of real images is lower; when using the proposed method of the present invention When the distance Dis measures image similarity, the distribution of real similar images in the result set is uniform, and the cloud server cannot judge the similarity information in the image from the result; The F1 in...

Embodiment 3

[0070] This embodiment specifically expounds how the present invention can be used to implement a secure image retrieval outsourcing function and to implement a multi-source image retrieval function based on encrypted images.

[0071] The image owner will encrypt the image according to step 1.1 before outsourcing the image. Suppose the image collection BCollection j One of the images in is (in order to illustrate the image encryption process, it is assumed that the image size is 9×9, in practice it depends on the size of the specific image):

[0072] B ji ={b j1 ,b j2 ,b j3 ,b j4 ,b j5 ,b j6 ,b j7 ,b j8 ,b j9}={30,23,45,236,89,70,66,51,198}

[0073] Image owner j will first generate an image encryption key, assuming the generated key is:

[0074] K j ={k j1 ,k j2 ,k j3 ,k j4 ,k j5 ,k j6 ,k j7 ,k j8 ,k j9}={187,253,56,78,12,45,68,99,100}

[0075] Then the encrypted image can be calculated as:

[0076]

[0077] For all images in the image set, the imag...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a multi-source encrypted image retrieval method supporting privacy protection, and belongs to the technical field of encrypted image retrieval. The method comprises the steps that thought encryption image features of secure multiparty computation is used, an image owner makes images, encrypted with a private key, of the owner and the image features outsourced to a cloud server, and the cloud server performs retrieval in an encrypted image library submitted by a user and returns the encrypted retrieval result to a query user. Accordingly, the image privacy protection problem occurring when multiple image owners outsource the images to a cloud for retrieval can be solved, the image owner and the user do not need a communication secret key, the communication cost is reduced, and the actual application prospect is better met; meanwhile, a new image similarity measurement method is provided, by means of the measurement method, the phenomenon that in the retrieval process, similarity information between the images stored in the cloud server is revealed to the cloud server can be prevented, and the private information of the images on the cloud server is further protected.

Description

technical field [0001] The invention relates to a multi-source encrypted image retrieval method supporting privacy protection, and belongs to the technical field of image encryption and image retrieval. Background technique [0002] In recent years, with the increasing abundance of network media, images, videos, etc. have become an indispensable part of people's lives in addition to text. The information expressed in images is not easy to describe in words, so image retrieval has become a a new requirement. The original image retrieval was based on the idea of ​​text retrieval. Firstly, each image was marked with keywords, and then retrieved based on these keywords, which is also called text-based image retrieval. However, with the rapid development of the network, there will be millions or even hundreds of millions of images generated on the network every second. At this time, labeling each image will consume huge manpower, material resources and financial resources. Late...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30H04L29/06H04L29/08
CPCG06F16/583H04L63/0428H04L67/10
Inventor 沈蒙程国华祝烈煌
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap