Irregular hole morphological defect image generation method

An image generation and irregular technology, which is applied in image analysis, image data processing, optical test defects/defects, etc., can solve the problems of inconsistency and hole shape defects that have not been involved by anyone, so as to reduce the iteration cycle and shorten the online cycle and model iteration cycle, avoiding the effect of overfitting problems

Active Publication Date: 2022-04-01
聚时科技(江苏)有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of defect image generation has been studied by some people (the design methods of different defects are different), but no one has been involved in the hole shape defects in semiconductor defect inspection.

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
  • Irregular hole morphological defect image generation method
  • Irregular hole morphological defect image generation method
  • Irregular hole morphological defect image generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] 1. Randomly select a normal image from the project data set as the background image generated by the defect, such as image 3 shown.

[0047] 2. Randomly sample the coordinate point in the set area as the center of the circle, and take the distance r as the radius to define a circle as the area where the hole shape defect is generated, such as Figure 4 shown. Randomly select n pixel coordinate points ...... in the picture as the contour points of the bottom area, where the positions of each point are respectively. ....., such as Figure 5 shown.

[0048] 3. Use the Bezier curve method to fit the contour points of the bottom area randomly selected in the previous step, and randomly select the shape factor K of the curve, where K belongs to [0.2,0.6]. The current K value is 0.3, and a result such as Image 6 The closed irregular circle in , the roundness of its contour area is greater than 0.5.

[0049] 4. The closed irregular circle generated in step 3 is defined ...

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 belongs to the technical field of machine vision detection, and particularly relates to an irregular hole morphological defect image generation method, which comprises the following steps: selecting a defect-free picture as a background image, randomly generating two closed irregular circles on the background image, nesting the two irregular circles, and filling the two irregular circles with different colors. According to the method, a large number of hole-shaped defect samples are randomly and rapidly generated by adopting an algorithm, the detection effect of a deep learning model can be rapidly improved in a short time, and the iteration period of the algorithm is greatly shortened.

Description

technical field [0001] The invention belongs to the technical field of machine vision detection, and in particular relates to a method for generating an irregular hole shape defect image. Background technique [0002] At present, in semiconductor defect detection projects, traditional image processing or deep learning are generally used for detection. Among them, traditional image processing requires manual design of rules, and developers must have a deep understanding of defects, which also leads to the emergence of problems such as weak robustness of design rules and difficulties in actual development. The development of deep learning algorithms makes it unnecessary to manually design features and repeatedly adjust parameters, but the defect detection effect depends on the data set of a large number of defect samples. In actual projects, the data of defect samples is often difficult to collect. The accuracy and robustness of the model are not ideal, which seriously affect...

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): G06T7/187G06T7/90G01N21/95G06T7/00G06T7/181
CPCY02P90/30
Inventor 彭仁杰
Owner 聚时科技(江苏)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