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

Building ceramic surface pattern quality detection method

A quality inspection method and technology for architectural ceramics, which are used in image enhancement, image analysis, image data processing, etc.

Active Publication Date: 2015-11-18
童垸林
View PDF7 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] At present, there is no public literature on the method of automatic detection of pattern quality on the surface of architectural ceramics based on salient object detection of deep neural network at home and abroad.

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
  • Building ceramic surface pattern quality detection method
  • Building ceramic surface pattern quality detection method
  • Building ceramic surface pattern quality detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] Embodiment one: see figure 1 As shown, a method for detecting the quality of decorative patterns on the surface of architectural ceramics comprises the following steps:

[0078] (1) Extract the salient features of the test samples:

[0079] (1) 500 image samples of building ceramic products to be tested, such as figure 2 , to calculate its visual saliency map, such as image 3 . The saliency model adopts a two-level strategy from coarse to fine. In the first level, a coarse saliency map is proposed by fusing contrast prior knowledge saliency map, center prior saliency map and boundary prior saliency map. In the second stage, a new energy equation is proposed by fusing the background energy term based on boundary prior knowledge, the data energy term based on rough saliency map and the smooth energy term based on smooth prior:

[0080] S * = arg ...

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 a building ceramic surface pattern quality detection method, comprising: combining a visual sense saliency model and a convolutional neural network model to automatically detective the saliency area of a building ceramic surface pattern; employing Grabcut to automatically divide a surface pattern; utilizing the convolutional neural network model to detect the quality of the surface pattern, thereby realizing high detection accuracy. The building ceramic surface pattern quality detection method can effectively detect building ceramic and colorful building ceramic surface pattern quality, save labor, and reduce labor intensity, and has high work efficiency and detection precision.

Description

technical field [0001] The invention belongs to a method for detecting the quality of decorative patterns on the surface of architectural ceramics, and is particularly suitable for the detection of colored architectural ceramics. Background technique [0002] The surface quality inspection of architectural ceramics in my country is still in its infancy, and the quality inspection of the surface of architectural ceramic products is mainly through manual measurement. Due to the high speed of building ceramic products on the production line, some inspections can only be carried out by random inspection, resulting in a high probability of missed inspections and false inspections. Therefore, the intelligent detection of the surface quality of architectural ceramics is very important in the quality control of architectural ceramic products. [0003] At present, most surface defect algorithms focus on the extraction of low-level features, which are artificially designed feature ex...

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
IPC IPC(8): G06T7/00
CPCG06T7/0004G06T2207/30168
Inventor 童垸林张汗灵胡峰松
Owner 童垸林