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

Convolutional neural network-based hardware defect segmentation method and system

A convolutional neural network and hardware technology, which is applied in the field of hardware defect segmentation methods and systems based on convolutional neural networks, can solve problems such as trachoma, material shortage, and low degree of automation, achieve accurate defect segmentation, and avoid low efficiency. , the effect of strong learning ability

Inactive Publication Date: 2018-09-28
GUANGDONG UNIV OF TECH
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The manual detection method is inefficient and the degree of automation is not high, and its accuracy is often related to the working experience and attitude of the testing personnel
At present, hardware product manufacturers are paying more and more attention to improving the level of production automation, and the requirements for production efficiency are getting higher and higher, and manual inspection methods are increasingly unable to meet the demand
In addition, in the process of production and processing, due to factors such as changes in the physical parameters of raw materials, unreasonable process parameters, and poor processing machinery performance, hardware products will have bruises, sand holes, scratches, lack of materials, deformation, pitting, oil stains, etc. on the surface defect
These surface defects will not only destroy the appearance of hardware products, but also affect its performance and make it unusable
At present, the surface defect detection and identification of hardware products are mainly manual, with low efficiency and low degree of automation

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
  • Convolutional neural network-based hardware defect segmentation method and system
  • Convolutional neural network-based hardware defect segmentation method and system
  • Convolutional neural network-based hardware defect segmentation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Please refer to the attached figure 1 , is a schematic flowchart of a hardware defect segmentation method based on a convolutional neural network provided by Embodiment 1 of the present invention. The method specifically includes the following steps:

[0052] S110. Construct an initial model of the convolutional neural network.

[0053] Among them, the convolutional neural network is a deep neural network proposed by LeCun, which can directly take a two-dimensional image as input without complex image preprocessing on the original image data. The convolutional neural network automatically extracts and combines features from images, and extracts image features of varying degrees of abstraction by increasing the depth of the network. Compared with traditional image processing algorithms, it does not need to manually select and describe features, and avoids a large number of calculations. In addition, convolutional neural networks can recognize changing patterns, are ro...

Embodiment 2

[0108] Please refer to the attached Figure 7 , is a schematic structural diagram of a hardware defect segmentation system based on a convolutional neural network provided in Embodiment 2 of the present invention, and the system is suitable for implementing the hardware defect segmentation method based on a convolutional neural network provided in an embodiment of the present invention. The system specifically includes the following modules:

[0109] Model building module 71, used to build the convolutional neural network initial model;

[0110] The model training module 72 is used to input the hardware defect images in the training set into the initial model of the convolutional neural network for training, so as to obtain the final model of the convolutional neural network;

[0111] The feature extraction module 73 is used to input the hardware defect images in the test set into the final model of the convolutional neural network to complete the extraction of high-dimension...

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

Embodiments of the invention disclose a convolutional neural network-based hardware defect segmentation method and system. The method comprises the following steps of: constructing a convolutional neural network initial model; inputting a hardware defect image in a training set into the convolutional neural network initial model to train so as to obtain a convolutional neural network final model;inputting a hardware defect image in a test set into the convolutional neural network final model so as to extract high-dimensional convolutional features, mapping the high-dimensional convolutional features into a surrounding box with a set size and a set long-width ratio, converting the surrounding box into a feature vector, and obtaining a center coordinate and a length of the defect surrounding box according to a conversion formula; and extracting features of a defect area according to the center coordinate and the length of the defect surrounding box so as to realize defect segmentation.Compared with the prior art, the method and system do not need to manually select and describe features, so that the problems of low efficiency, instability, large calculated amount and low automationdegree in manual segmentation are avoided.

Description

technical field [0001] Embodiments of the present invention relate to the field of visual inspection in image processing, and in particular to a hardware defect segmentation method and system based on a convolutional neural network. Background technique [0002] Machine vision, also known as computer vision, is a science that studies the use of cameras and computers to imitate human eyes and brains, so that machines can replace humans for detection and judgment, and complete tasks such as target recognition and industrial inspection. Machine vision technology is an applied technical discipline that integrates digital image processing, artificial intelligence, computer graphics and other disciplines, and is widely used in automated production. In recent years, the advancement of computer technology and the continuous improvement of neural network theory have promoted the rapid development of computer vision. The rapid development of my country's machine vision industry occup...

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): G06T7/11G06N3/04
CPCG06T7/11G06N3/045
Inventor 王宏杰李海艳黄运保
Owner GUANGDONG UNIV OF TECH