Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Bathroom ceramic surface defect detection method

A ceramic surface and defect detection technology, applied in neural learning methods, image data processing, biological neural network models, etc., can solve the problem that the detection accuracy and detection speed cannot meet the bathroom ceramic defect detection, etc. The effect of wide range and fast detection speed

Pending Publication Date: 2022-02-18
BEIJING RES INST OF AUTOMATION FOR MACHINERY IND
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the detection accuracy and detection speed of the existing technology cannot meet the needs of defect detection in the actual production of sanitary ceramics

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
  • Bathroom ceramic surface defect detection method
  • Bathroom ceramic surface defect detection method
  • Bathroom ceramic surface defect detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with accompanying drawing, structural principle and working principle of the present invention are specifically described:

[0030] see figure 1 , figure 1 It is a method flow chart of an embodiment of the present invention. Sanitary ceramic surface defect detection method of the present invention, based on improving CenterNet, such as figure 1 shown, including the following steps:

[0031] Step S100, collect the original image of sanitary ceramics (for example, you can go to the production base), and construct a data set of surface defect images of sanitary ceramics;

[0032] Step S200, using data enhancement technology to expand the surface defect images of sanitary ceramics, and then using image calibration software to make all the surface defect images of sanitary ceramics according to the format of the data set VOC 2007 into a data set of surface defects of sanitary ceramics;

[0033] Step S300, using Tensorflow and Keras open source deep l...

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

A bathroom ceramic surface defect detection method comprises the following steps: collecting an original image of bathroom ceramic, and constructing a bathroom ceramic surface defect image data set; expanding bathroom ceramic surface defect images, and then making all the bathroom ceramic surface defect images into a bathroom ceramic surface defect data set; constructing an improved Center Net defect detection model by utilizing a Tensorflow and Keras open source deep learning framework; inputting bathroom ceramic defect images into the improved Center Net defect detection model in batches, and iteratively training the model to finally obtain a bathroom ceramic surface defect detection model; after the training is completed, inputting a test set sample into the bathroom ceramic surface defect detection model, and verifying the robustness of the improved Center Net defect detection model; and inputting a bathroom ceramic surface defect image to be detected into the tested bathroom ceramic surface defect detection model, and carrying out defect detection. According to the invention, manual defect detection can be replaced, and the detection efficiency and the detection precision are obviously improved.

Description

technical field [0001] The invention relates to ceramic defect detection technology, in particular to a method for detecting surface defects of sanitary ceramics based on improved CenterNet. Background technique [0002] China is the world's largest producer and seller of sanitary ceramics. There are many manufacturers in the sanitary ceramics industry, and the degree of automation of the entire industry is steadily improving. However, the quality inspection of finished sanitary ceramics is far from enough, mainly relying on manual inspection by inspectors. The detection efficiency is low, and it is easily affected by the experience factors and physical condition of the test personnel. [0003] In recent years, with the development of computer technology, deep learning technology has also made great progress, and more and more enterprises have begun to use deep learning technology for defect detection. Compared with existing detection technologies, defect detection based on...

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): G06T7/00G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06N3/08G06T2207/20081G06T2207/20084G06T2207/30108G06N3/048G06N3/045G06F18/241
Inventor 赵宏剑贾沛田成花滕博文顾聪
Owner BEIJING RES INST OF AUTOMATION FOR MACHINERY IND
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products