Ciphertext JPEG image retrieval method and application

A plaintext image and image technology, which is applied in the direction of still image data retrieval, metadata still image retrieval, special data processing applications, etc., can solve the problems of technical retrieval efficiency and low performance, information leakage, etc., and achieve high retrieval effect and safe storage In the server, the effect of solving information leakage

Pending Publication Date: 2021-02-26
JINAN UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] So far, many ciphertext image retrieval technologies have been proposed, but some technologies cause information leakage, and some technologies have low retrieval efficiency and performance.

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
  • Ciphertext JPEG image retrieval method and application
  • Ciphertext JPEG image retrieval method and application
  • Ciphertext JPEG image retrieval method and application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, the present embodiment provides a method for ciphertext JPEG image retrieval, combining Huffman codes and neural networks, mainly including three parts: content owner, server and authorized user, wherein, the content owner encrypts the JPEG image so that Protect privacy, and then store the encrypted image in the server; the server parses the JPEG bit stream extraction feature according to the ciphertext database, extracts the Huffman code histogram feature of the ciphertext image, and uses it as the input of the network model, according to the input feature Train a network model and save the trained network model in the server. When an authorized user needs to retrieve an image, he only needs to provide the ciphertext image of the image to be retrieved to the server, and then input the Huffman code histogram feature of the ciphertext image into the saved network model, and find similar images according to the output results. image, and return...

Embodiment 2

[0072] The present embodiment provides a retrieval system of a ciphertext JPEG image, comprising: an image encryption module, a feature extraction module, a neural network model building module, a neural network model training module and an image retrieval module;

[0073] In this embodiment, the image encryption module is used to encrypt the plaintext image, obtain the plaintext image and the corresponding DC coefficients and AC coefficients, and encrypt the bitstream during entropy coding to generate the bitstream to obtain an encrypted JPEG bitstream, and Extract features in the encrypted JPEG bitstream;

[0074] In this embodiment, the feature extraction module is used to analyze the ciphertext JPEG bit stream to extract features, and extract the Huffman code histogram of the DC coefficient and the AC coefficient as a feature;

[0075] In this embodiment, the neural network model construction module is used to construct the neural network model;

[0076] In this embodimen...

Embodiment 3

[0079] This embodiment provides a storage medium. The storage medium may be a storage medium such as ROM, RAM, magnetic disk, or optical disk. The storage medium stores one or more programs. A method for document JPEG image retrieval.

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 discloses a ciphertext JPEG image retrieval method and application, and the method comprises the steps: obtaining a plaintext image and a corresponding DC coefficient and AC coefficient,carrying out the image encryption of the plaintext image, carrying out the encryption of a bit stream generated through entropy coding, obtaining an encrypted JPEG bit stream, and extracting featuresfrom the encrypted JPEG bit stream; analyzing the ciphertext JPEG bit stream to extract features, and extracting Huffman code histograms of the DC coefficient and the AC coefficient as features; constructing a neural network model, inputting the Huffman code histogram features of the ciphertext image into the neural network model, and training the neural network model; and inputting the encryptedciphertext graph of the to-be-retrieved image, inputting the Huffman code histogram features of the ciphertext graph into the trained neural network model, and outputting a ciphertext image similar to the to-be-retrieved image. According to the method, the image retrieval precision is improved, and the JPEG image format compatibility and encryption performance are ensured.

Description

technical field [0001] The invention relates to the technical field of image encryption and retrieval, in particular to a retrieval method and application of ciphertext JPEG images. Background technique [0002] In recent years, due to the rapid development of digital services, a large number of images are shared on various social networks, such as Facebook and Instagram. Usually, image data contains rich information and can be used for different purposes, such as feature extraction and image retrieval. With the emergence of cloud computing, the traditional local storage mode has been changed, which meets the needs of users to store a large amount of image data in the server, and at the same time allows users to access it anytime and anywhere. Although cloud computing has brought great convenience to users, due to the consideration of data privacy protection, data is often encrypted before uploading. The traditional image encryption algorithm hinders further meaningful oper...

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): G06F16/58G06F21/60
CPCG06F21/602G06F16/5866
Inventor 冯齐华翁健黄斐然李佩雅卢植勋
Owner JINAN UNIVERSITY
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