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

Visual saliency-based method for determining surface defects

A judging method and remarkable technology, which is applied in the direction of optical testing flaws/defects, image data processing, instruments, etc., can solve problems such as false detection of significant areas, and achieve the effects of simple and practical algorithms, exclusion of influence, and high accuracy

Active Publication Date: 2017-08-01
SUZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When there is a defect in the image of the detected object, its salient area is the defect area; when there is no defect, the salient area may be falsely 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
  • Visual saliency-based method for determining surface defects
  • Visual saliency-based method for determining surface defects
  • Visual saliency-based method for determining surface defects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Embodiment one: see figure 1 As shown, a method for judging surface defects based on visual salience includes the following steps:

[0023] (1) Use a linear CCD camera to collect n surface image samples of the product to be inspected;

[0024] (2) Calculate the visual saliency map of n surface image samples of the product to be tested using the visual saliency model;

[0025] (3) Use the fast maximum between-class variance method to segment the first visual saliency map , and find its threshold ;

[0026] Described visual saliency map comprises the saliency map that different visual saliency models obtain, selects Itti model, GBVS model to analyze the visual saliency map of chemical fiber cloth image gain in the present embodiment, see figure 2 and 3 shown.

[0027] Let the gray level in the saliency map be The number of pixels is , the grayscale range is , the pixels in the figure are thresholded into two categories and , the total variance of th...

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 surface defect judgment method based on visual saliency. The method comprises the following steps: firstly, acquiring a surface image sample of a to-be-detected product and calculating a visual saliency map by a saliency map model; secondly, performing threshold segmentation on a salient image; thirdly, calculating the characteristic value of the saliency map; finally, selecting a characteristic value threshold and judging whether a defect exists in the image or not. According to the method, an algorithm is simple and practical, the accuracy is high, and the influence of surface folds on defect detection is eliminated.

Description

technical field [0001] The invention relates to a method for judging surface defects, in particular to a method for judging defects based on visually significant surface defect images. Background technique [0002] The detection of surface defects on objects is important for the quality control of many production processes. Because the traditional human eye online detection method is easy to cause false detection, missed detection and human eyesight fatigue, so the research on automatic detection and detection system is of great significance. [0003] Humans can quickly and effectively identify defects, regardless of the intensity of reflection, defect properties, and changes in texture structure. Human beings have powerful image understanding and pattern recognition capabilities, and imitate the human visual mechanism based on visual saliency, and have been extensively researched on surface defect detection methods for paper, steel strip, cloth, film, etc. in industrial pr...

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 Patents(China)
IPC IPC(8): G06T7/40G01N21/88
CPCG01N21/88
Inventor 何志勇胡佳娟杨宏兵翁桂荣孙立宁左保齐王晨
Owner SUZHOU UNIV