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

Circuit board surface defect detection method based on polarization prior

A defect detection and circuit board technology, applied in the field of defect detection, can solve problems such as low efficiency and difficult detection, and achieve the effects of reducing interference, preventing overfitting, and reducing weight parameters.

Pending Publication Date: 2022-05-27
RES & DEV INST OF NORTHWESTERN POLYTECHNICAL UNIV IN SHENZHEN +1
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for detecting defects on the surface of a circuit board based on polarization prior to solve the problem of low efficiency when using traditional image processing methods in the prior art, and the difficulty of using a single input method based on deep learning. Issues to detect all defects

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
  • Circuit board surface defect detection method based on polarization prior
  • Circuit board surface defect detection method based on polarization prior
  • Circuit board surface defect detection method based on polarization prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] In the embodiment of the present invention, the visible light image includes the visible light polarization image obtained by demosaicing and the difference image corresponding to the vertical direction, and the polarization degree and polarization angle images include the visible light polarization degree image and the visible light polarization angle image calculated from the visible light polarization image. When inputting the deep neural network, all images are superimposed by channel to form a three-dimensional tensor, which is expressed as Among them, C, H, and W are the number of channels, height and width of the tensor, respectively. After the pre-trained network operation, the probability of a defect within the range of a candidate frame and the position and width and height of the candidate frame are output. information.

[0043] Based on the above embodiments, further, the structure of the deep neural network for defect detection is explained below. figure...

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 circuit board surface defect detection method based on polarization prior. The method comprises the following steps: S1, acquiring an infrared intensity image and a visible light polarization image of a detected circuit board; s2, performing demosaicing operation on the visible light polarization image to obtain a Stokes vector image, and calculating according to the Stokes vector image to obtain a visible light polarization degree image and a visible light polarization angle image; and S3, inputting the infrared intensity image and the visible light polarization image obtained in the S1 and the visible light polarization degree image and the visible light polarization angle image obtained in the S2 into a pre-trained deep neural network to obtain a defect detection result. The problems that in the prior art, efficiency is low when a traditional image processing method is used for detection, and all defects are difficult to detect through a single-input deep learning-based method are solved.

Description

technical field [0001] The invention belongs to the technical field of defect detection, and in particular relates to a method for detecting surface defects of circuit boards based on polarization prior. Background technique [0002] As a basic part of electronic equipment, the importance of circuit boards is self-evident. With the increasing complexity of circuit board design, the integration of components is getting higher and higher. In the actual production process, due to various reasons such as fluctuations in the production environment and non-standard manufacturing processes, it is inevitable that defects will occur on the surface of electronic products and various components in the production process. These defects affect product performance and cause huge economic losses to users. At present, the artificial visual detection method has shortcomings such as strong subjectivity, limited spatial resolution of the human eye, and large uncertainty, which can no longer m...

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): G06T7/00G06N3/04G06N3/08G01N21/956
CPCG06T7/0004G06N3/08G01N21/956G06T2207/10048G06T2207/20081G06T2207/20084G06T2207/20221G06T2207/30141G01N2021/95638G06N3/045
Inventor 赵永强姚乃夫李梦珂
Owner RES & DEV INST OF NORTHWESTERN POLYTECHNICAL UNIV IN SHENZHEN