Image difference comparison method and system, and electronic device

A technology of difference ratio and matching method, which is applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of poor robustness and accuracy, and achieve improved accuracy and robustness, fast speed, Robust Effect

Active Publication Date: 2019-05-10
创新奇智(北京)科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the technical problems of the poor robustness and accuracy of the image comparison method in the prior art, the present invention provides a novel image difference comparison method and its system and electronic device

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
  • Image difference comparison method and system, and electronic device
  • Image difference comparison method and system, and electronic device
  • Image difference comparison method and system, and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032]In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0033] see figure 1 , the first embodiment of the present invention provides an image difference comparison method, the image difference comparison method includes the following steps:

[0034] Step S1, acquiring two images to be compared to be compared;

[0035] Step S2, select any one of the images to be compared, and based on the convolutional neural network, select one of the pixels and establish a function f(x i ,x j ), based on the function f(x i ,x j ) to know the weight of the pixel in the global images to be compared, and so on, until all the pixels in the two images t...

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 relates to an image difference comparison method and system, and an electronic device, and the method comprises the steps: selecting one pixel point based on a convolutional neural network to establish a function f(xi,xj) with all to-be-compared global pixels of an image, and obtaining the weight of the pixel point in the global image to be subjected to difference comparison based onthe function f(xi,xj); and further selecting a feature vector g (xj) of at least one feature pixel point and multiplying the feature vector g (xj) with the plurality of functions to output a corresponding feature map. On the basis of the method, global information can be better embodied in the output feature map, self-learning is achieved, and due to the fact that different pixel points obtain different weight values based on the global information of the to-be-differentially-compared images, the accuracy and robustness of obtaining the difference information of the two to-be-differentially-compared images based on the feature map can be improved.

Description

【Technical field】 [0001] The invention relates to the field of artificial intelligence, in particular to an image difference comparison method, a system thereof, and an electronic device. 【Background technique】 [0002] The existing comparison methods for finding image differences are all based on traditional image methods. According to image processing methods such as filter transformation, it is not completely correct to find out the difference between two images based on the area where the pixels of the two images change. Identify the difference area. In addition, because the existing image feature extraction is more focused on the change of the pixel, it is often easy to make judgment and comparison errors due to the difference in the shooting angle of the picture, the simple change of the position or the shape. Therefore, the existing image comparison method The robustness (Robustness) is not good, the accuracy is not good, and it is urgent to provide a new type of imag...

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): G06K9/62
Inventor 张发恩吴佳洪秦永强
Owner 创新奇智(北京)科技有限公司
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