Method and device for automatically generating crystal grain detection sample

An automatic generation and grain technology, applied in image data processing, instruments, calculations, etc., can solve the problems of large number of samples, inaccurate manual alignment, difficult selection, etc., to achieve the effect of accurate position and avoid errors

Active Publication Date: 2021-10-29
武汉精创电子技术有限公司
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method for automatically generating grain inspection samples and an automatic generation device for grain inspection samples, which can solve the problem of traditional Golden Die manually screening inspection images and then performing manual inspection. There are problems such as large number of samples, inability to take pictures of some grains, resulting in difficulty in selection and inaccurate manual alignment.

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
  • Method and device for automatically generating crystal grain detection sample
  • Method and device for automatically generating crystal grain detection sample
  • Method and device for automatically generating crystal grain detection sample

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0042] like figure 1 As shown, the first embodiment of the present invention proposes a method for automatically generating a grain inspection sample, comprising the following steps: Step S11 acquires multiple grain inspection images of a plurality of grains of the same type; Detecting overlapping regions between images, performing image alignment and obtaining sub-region images corresponding to each sub-region of a plurality of said crystal grains; step S13 selecting the sub-region image with the largest number of occurrences in the same sub-region as the sub-region image Standard grain images corresponding to the subregions.

[0043] In step S11, the same type of grain mentioned is the grain with the same appearance characteristics among different individuals. When performing grain defect detection, multiple grains of the same type can be distributed on the same wafer (wafer) , and can also be distributed on different wafers. For example, a camera or other equipment is use...

no. 2 example

[0054] like Figure 4 As shown, the second embodiment of the present invention proposes an automatic generation device 20 for grain inspection samples, including, for example, a grain inspection image acquisition module 201 , a sub-region image acquisition module 202 , and a standard grain image selection module 203 .

[0055] Wherein, the grain detection image acquisition module 201 is used to acquire multiple grain detection images of multiple grains of the same type. The sub-region image acquisition module 202 is configured to perform image alignment according to overlapping regions among the multiple inspection images of the crystal grains and acquire sub-region images corresponding to each sub-region of the multiple crystal grains. The standard grain image selection module 203 is used to select the sub-region image that appears most frequently in the same sub-region as the standard grain image corresponding to the sub-region.

[0056] Further, such as Figure 5 As shown...

no. 3 example

[0061] like Figure 8 As shown, the third embodiment of the present invention proposes an automatic generation system 30 for grain inspection samples, for example including: a memory 32 and one or more processors 31 connected to the memory 32 . The memory 32 stores a computer program, and the processor 31 is used to execute the computer program to realize the method for automatically generating a grain inspection sample as described in the first embodiment. For the specific automatic generation method of grain detection samples, please refer to the method described in the first embodiment, which will not be repeated here for the sake of brevity, and the beneficial effect of the automatic generation system 30 for grain detection samples provided by this embodiment is the same as that of the first embodiment The beneficial effects of the provided method for automatically generating grain inspection samples are the same.

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 method for automatically generating a crystal grain detection sample. The method comprises the following steps: acquiring a plurality of crystal grain detection images of a plurality of crystal grains of the same type; carrying out image alignment according to an overlapping region among the plurality of crystal grain detection images, and obtaining a fixed region image corresponding to each crystal grain; and screening according to the fixed area images among different crystal grains, and selecting the fixed area image with the highest occurrence frequency as a crystal grain detection sample. According to the method, the problems of difficulty in selection and inaccurate manual alignment caused by a large number of samples and incapability of completely shooting part of crystal grains when the traditional Golden Die obtains images through manual screening and detection and then performs manual alignment can be solved.

Description

technical field [0001] The invention relates to the technical field of semiconductor detection, in particular to a method for automatically generating a sample for crystal grain detection and an automatic generation device for a sample for crystal grain detection. Background technique [0002] Die defect detection is an essential process in semiconductor production. In the detection of grain defects, it is required to be able to output the difference between each grain and the sample based on the samples of normal grains, and judge whether it is a defect. However, how to select a sample is a difficult challenge. The difficulty is that due to the unstable optical conditions during shooting, there will be problems such as distortion, bright and dark fields, etc. At the same time, sometimes one picture of the grain size cannot fully cover it, and there will be multiple pictures of different parts of the same grain, and it will be more difficult to obtain a "standard" at this ...

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): G06T7/00G06T7/80G06T5/00G06T3/40
CPCG06T7/001G06T7/80G06T5/006G06T3/4038G06T2207/30148
Inventor 刘荣华熊柏泰
Owner 武汉精创电子技术有限公司
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