Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

X-ray image examination method, device, electronic equipment and storage medium

A detection method and light image technology, applied in the field of deep learning, can solve problems such as low item recognition rate

Active Publication Date: 2018-03-23
ZHEJIANG DAHUA TECH CO LTD
View PDF9 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides an X-ray image detection method, device, electronic equipment and storage medium to solve the problem of low object recognition rate in the prior art

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
  • X-ray image examination method, device, electronic equipment and storage medium
  • X-ray image examination method, device, electronic equipment and storage medium
  • X-ray image examination method, device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 A schematic diagram of an X-ray image detection process provided by an embodiment of the present invention, the process includes the following steps:

[0053] S101: Input the first X-ray image to be detected into the pre-trained item detection model, wherein the item detection model saves a weight parameter file that has been trained by the neural network, and the weight parameter file includes predictions. For items of the category, coordinate weights corresponding to a preset number of vertices, wherein the preset number is at least four.

[0054] The X-ray object detection method provided by the embodiment of the present invention is applied to an electronic device, such as a desktop computer, a portable computer, a tablet computer, etc., and the electronic device can receive the first X-ray image to be detected. In an X-ray security inspection scenario, the electronic device may be an X-ray security inspection machine, and the electronic device may collect...

Embodiment 2

[0072] In order to eliminate the interference factors in the X-ray image and further improve the item recognition rate, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, the input of the first X-ray image to be detected into the pre-trained item detection Before the model, the method also includes:

[0073] Preprocessing the first X-ray image to be detected;

[0074] Said inputting the first X-ray image to be detected into the pre-trained item detection model includes:

[0075] Inputting the preprocessed first X-ray image into the item detection model.

[0076] The first X-ray image is preprocessed, and the preprocessed first X-ray image is input into the item detection model, so that the interference factors in the first X-ray image are eliminated, and the output result of the item detection model is more accurate, thereby Further improved the item recognition rate.

[0077]The process of preprocessing the first X-ray image to be ...

Embodiment 3

[0080] In order to obtain the weight parameter file, the item detection model needs to be trained. On the basis of the above-mentioned embodiments, in the embodiment of the present invention, the training process of the item detection model based on the neural network includes:

[0081] For each second X-ray image in the training set, obtain the second coordinates of a preset number of vertices corresponding to each item manually marked in the second X-ray image, and the second category to which each item belongs;

[0082] According to the obtained second coordinates of the preset number of vertices corresponding to each item in the second X-ray image, and the second category to which each item belongs, and inputting the second X-ray image into an item detection model , obtain the third coordinates of the preset number of vertices corresponding to each item and the third category to which each item belongs, perform iterative training on the item detection model, and modify the ...

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 an X-ray image examination method, a device, electronic equipment and a storage medium. The X-ray image examination method comprises the steps of inputting a to-be-examined first X-ray image into a pre-trained object examining model, wherein a weight parameter file which is trained by a neural network is stored in the object examining model, and the weight parameter file comprises coordinate weights which correspond with a preset number of summits in predicating different kinds of objects; based on the object examining model, determining the first kind of each object which is included in the first X-ray image, and the first coordinates of the preset number of summits which correspond with each object, wherein the preset number is four at least; and according to thefirst kind of each object and the first coordinates of the preset number of summits which correspond with each object, marking each object in the first X-ray image. A polygon which is marked accordingto the X-ray image examination method is closer to the true contour of the object.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to an X-ray image detection method, device, electronic equipment and storage medium. Background technique [0002] The item detection method is mainly used in the item detection of X-ray security inspection machines. For example, it is specifically used to detect whether there are items in the luggage of passengers in public places such as high-speed rail, subway, and airplane. The purpose of using X-ray security inspection machines is to assist security personnel to quickly , Effectively discover the items that may exist in the package, and reduce the opening and inspection as much as possible. Security inspectors judge whether there is an item through the X-ray image on the screen of the security inspection machine, but factors such as high-speed rail, subway and other places with a large flow of people, more bags, and long hours of work will affect the accuracy of t...

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): G06T7/00G06T7/73G06N3/08G01V5/00
CPCG06N3/084G06T7/0004G06T7/73G06T2207/30208G06T2207/20081G06T2207/20084G06T2207/10116G01V5/22
Inventor 孙海涛徐阳付建海
Owner ZHEJIANG DAHUA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com