Lipstick defect detection device based on attention capsule network and detection method thereof

A defect detection and attention technology, applied in measurement devices, optical testing of defects/defects, material analysis by optical means, etc., can solve problems such as poor robustness and single function, and achieve the effect of convenient inspection and reduced labor intensity.

Inactive Publication Date: 2020-11-17
上海可明信息科技有限公司
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention patent with the patent application number CN201810831640.5 discloses "Insulator defect identification and positioning device and method based on capsule network". The main problem is that the application of capsule network is only used for target detection, while the actual defect identification is realized by traditional image processing methods , and the defects are not classified, and the function is relatively single. In addition, the defect marking process is not implemented by the capsule network, but by the pixel comparison method, which is less robust

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
  • Lipstick defect detection device based on attention capsule network and detection method thereof
  • Lipstick defect detection device based on attention capsule network and detection method thereof
  • Lipstick defect detection device based on attention capsule network and detection method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] A lipstick defect detection device based on attention capsule network, such as figure 1 Shown, comprise image acquisition system 100 and lipstick defect detection system 200; Wherein image acquisition system 100 comprises camera 101 and network client 102, camera 101 is used for taking the lipstick image of 4 directions of lipstick to be checked, and network client 102 is used for Store the captured lipstick image locally;

[0031] The lipstick defect detection system 200 comprises a network server 201, a lipstick detection module 202 and a defect visualization module 203, wherein the network server 201 is used to receive the lipstick image sent by the network client 102 and transmit it to the lipstick detection module 202 for defect detection, and The detection results are displayed through the defect visualization module 203 .

[0032] The lipstick defect detection device of this embodiment realizes the visual detection of lipstick defect parts through the visual pre...

Embodiment 2

[0034] A detection method such as figure 2 As shown, it is used for defect detection on lipstick images, including the following steps:

[0035] Step 1: The camera 101 takes pictures of the lipstick images in 4 directions of the lipstick to be inspected, transmits the lipstick images to the network client 102 for local storage, and creates a visual interface of the lipstick images through the defect visualization module 203;

[0036] Step 2: Load the defect detection and positioning module into the main program of the lipstick detection module 202 in advance, for the main program to import the image, and load the attention capsule network model to the GPU (image processor) of the lipstick detection module 202 in advance In video memory;

[0037] Step 3: the main program of the lipstick detection module 202 receives the lipstick image of the network server 201, and loads the attention capsule network model to perform defect detection on the lipstick image;

[0038] Step 4: S...

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 relates to the technical field of intelligent quality inspection of products, in particular to a lipstick defect detection device based on an attention capsule network, which comprises an image acquisition system including a camera and a network client, wherein the camera is used for shooting lipstick images of a lipstick to be detected in four directions, and the network client is used for locally storing the shot lipstick image; a lipstick defect detection system, which comprises a network server, a lipstick detection module and a defect visualization module, wherein the network server is used for receiving the lipstick image sent by the network client and transmitting the lipstick image to the lipstick detection module for defect detection, and a detection result is displayed through the defect visualization module. The detection method is used for carrying out defect detection on the lipstick image; compared with a traditional work flow, the quality defect of the lipstick is easier to find, and the labor intensity of quality inspection personnel can be reduced, so that the work efficiency is improved, and the quality inspection stability is improved.

Description

technical field [0001] The invention relates to the technical field of product intelligent quality inspection, in particular to a lipstick defect detection device and a detection method based on an attention capsule network. Background technique [0002] At present, the production line of lipstick production enterprises has not yet reached the level of full automation, and many links require manual intervention throughout the entire process. Among them, the quality inspection part is one of the bottlenecks for production capacity improvement, and there is an upper limit for the efficiency of manual quality inspection; It will harm the quality inspection workers, and the accuracy of quality inspection will decrease with time; manual quality inspection even if the workers are full of energy, there are still cases of missed inspections and false inspections. [0003] After retrieval, the invention patent with the patent application number CN201810831640.5 discloses "Insulator D...

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 & AuthorityApplications(China)
IPC IPC(8): G01N21/88
CPCG01N21/8851G01N2021/8887
Inventor黄鹏董亮王海峰
Owner上海可明信息科技有限公司