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

Mask appearance defect detection system, method and device and storage medium

A technology for appearance defects and defect locations, which is applied in the field of devices, storage media, methods, and mask appearance defect detection systems, can solve a large number of problems such as detection accuracy of quality inspectors, human subjective influence, and difficulty in achieving efficient automatic detection, and achieves a reduction in the huge number of problems. Sample requirements, the effect of improving coverage and precision, and improving flexibility and stability

Pending Publication Date: 2020-10-13
北京滴普科技有限公司
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present disclosure provide a mask appearance defect detection system, method, device, and storage medium to at least solve the mask appearance defect detection method in the prior art mainly using manual detection and detection of visual equipment based on traditional visual algorithms method, because the manual detection method requires a large number of quality inspectors and the detection accuracy is affected by human subjectivity, and the detection method of visual equipment based on traditional visual algorithms often needs to adjust parameters many times when changing product styles, which is difficult to achieve efficient automation Technical issues detected

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
  • Mask appearance defect detection system, method and device and storage medium
  • Mask appearance defect detection system, method and device and storage medium
  • Mask appearance defect detection system, method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] According to this embodiment, an embodiment of a mask appearance defect detection method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, although A logical order is shown in the flowcharts, but in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0028] The method embodiments provided in this embodiment can be executed in a server or similar computing devices. figure 1 A block diagram of a hardware structure of a computing device for implementing a method for detecting defects in the appearance of a mask is shown. Such as figure 1 As shown, the computing device may include one or more processors (processors may include but not limited to processing devices such as microprocessors MCUs or programmable logic devices FPGAs), memory for storing data, and memory fo...

Embodiment 2

[0087] Figure 11 Shown is the mask appearance defect detection device 1100 according to this embodiment, and the device 1100 corresponds to the method according to the second aspect of the first embodiment. refer to Figure 11 As shown, the device 1100 includes: an acquisition module 1110 for acquiring a mask image of a mask to be detected for appearance defects; a determination module 1120 for determining whether there is an appearance defect in the mask according to the mask image; a detection module 1130 for determining whether there is an appearance defect in the mask In the case that there is an appearance defect in the mask, the mask image is detected using a pre-trained appearance defect detection model to determine the defect position information of the appearance defect in the mask image; and a model optimization module 1140 is also included for performing an appearance defect detection model Optimizing, wherein the model optimization module 1140 includes: generatin...

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 mask appearance defect detection system, method and device and a storage medium. The system comprises an image processing server and an image acquisition device used for acquiring mask images of masks with appearance defects to be detected, wherein the image acquisition device is connected with the image processing server, and the image processing server is configured toexecute the following operations: receiving the mask images from the image acquisition device, judging whether the mask has appearance defects according to the mask image, under the condition that itis judged that the appearance defect exists in the mask, detecting the mask image by using a pre-trained appearance defect detection model, determining the defect position information of the appearance defect in the mask image, and optimizing the appearance defect detection model through the following operations: generating a plurality of sample defect images by using a preset CGAN model and maskdefect images with appearance defects acquired by the image acquisition device, and retraining the appearance defect detection model by using the plurality of sample defect images.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a mask appearance defect detection system, method, device and storage medium. Background technique [0002] At present, the mainstream method of quality inspection of flat masks is to use manual or visual equipment based on traditional visual algorithms for inspection. The manual detection method requires a large number of quality inspectors for mask appearance defects, and the detection accuracy is affected by human subjectivity; the use of visual equipment based on traditional visual algorithms often requires multiple adjustments of parameters when changing product styles, making it difficult to achieve efficient automation detection. [0003] In view of the mask appearance defect detection method in the above-mentioned prior art, manual detection and the detection method of visual equipment based on traditional visual algorithms are mainly used. Beca...

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): G06T7/00G06K9/62G06N3/04G06N3/08G01N21/88
CPCG06T7/0004G06N3/084G01N21/8851G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/30108G01N2021/8887G06N3/045G06F18/2321G06F18/2415
Inventor 钟宗余赵正阳
Owner 北京滴普科技有限公司