Unlock instant, AI-driven research and patent intelligence for your innovation.

A Hog Image Feature Extraction Algorithm Based on Vector Homomorphic Encryption

An image feature extraction and homomorphic encryption technology, applied in the field of image processing, can solve the problems of being easily mined and analyzed by the cloud or others, and unable to balance efficiency and accuracy at the same time

Active Publication Date: 2019-10-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The purpose of the present invention is to solve (1) the privacy report of the existing HOG image feature extraction algorithm, which is easy to be mined and analyzed by the cloud or others; (2) the gradient direction of the HOG image feature extraction algorithm is 9, and the efficiency cannot be taken into account at the same time and the problem of accuracy, the present invention provides a HOG image feature extraction algorithm based on vector homomorphic encryption, compared with the previous homomorphic encryption scheme based on single bit or single integer encryption, it greatly improves the computational efficiency in the ciphertext domain

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
  • A Hog Image Feature Extraction Algorithm Based on Vector Homomorphic Encryption
  • A Hog Image Feature Extraction Algorithm Based on Vector Homomorphic Encryption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] For an image I of size n × m to be detected, the steps of the HOG image feature extraction algorithm based on vector homomorphic encryption are as follows:

[0057] An image I to be detected with a size of n×m, HOG feature extraction steps in the ciphertext domain:

[0058] Step 1: Grayscale an image (target to be detected or scanning window) to obtain a grayscale image;

[0059] Step 2: standardization (normalization) of the color space is carried out by adopting the Gamma correction method to the grayscale image to obtain the image I;

[0060] Step 3: The user generates a key S, encrypts the image I using the VHE homomorphic encryption scheme, and obtains a ciphertext vector group; regards each row of the image I as an integer vector, and encrypts it row by row get ciphertext vector set where I i (x, y) represents the pixel value of the ith row of the image I.

[0061] Calculate its gradient values ​​in four directions of 0°, 45°, 90°, and 135° for the ciphertex...

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 HOG image feature extraction algorithm based on vector homomorphic encryption, which relates to the technical field of image processing. Since the VHE homomorphic encryption scheme only supports operations between integers and does not support division in the ciphertext domain, it is aimed at what VHE can support. Operation, reasonably cropping and improving the existing HOG image feature extraction algorithm, simplifying some feature extraction steps, and equivalently converting some complex operations in the extraction process to ensure that the cropped algorithm can guarantee a certain algorithm efficiency Under the premise of , the extracted feature vector is equivalent to the feature vector extracted by the original HOG feature extraction algorithm, and both can accurately express image features. The vector-based homomorphic encryption scheme VHE adopted in this scheme can directly encrypt an integer vector and support some operations based on ciphertext vectors. Compared with the previous homomorphic encryption scheme based on single bit or single integer encryption , greatly improving the computational efficiency in the ciphertext domain.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a HOG image feature extraction algorithm based on vector homomorphic encryption. Background technique [0002] Histogram of Oriented Gradient (HOG) feature is a feature descriptor used for object detection in computer vision and image processing. It constructs features by computing and counting the gradient direction histograms of local regions of the image. The core idea of ​​HOG is that the detected local object shape can be described by the distribution of light intensity gradient or edge direction. By dividing the entire image into small connected regions (called cells), each cell generates a histogram of directional gradients or the edge directions of the pixels in the cell. The combination of these histograms can represent the (target of the detected target) description son. To improve accuracy, the local histogram can be contrast-normalized by computing the lig...

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 Patents(China)
IPC IPC(8): G06T1/00G06K9/46
CPCG06T1/0021G06V10/50
Inventor 杨浩淼黄云帆何伟超冉鹏姚明轩金保隆
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA