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

An image detection method for surface defects of silicon steel plate under the interference of oil pollution

A technology of image detection and silicon steel plate, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of target information coverage, increase the difficulty of target detection and recognition, and achieve the effect of avoiding false edges

Active Publication Date: 2017-03-22
NORTHEASTERN UNIV LIAONING
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, target information may still be covered by disturbances in the obtained defect images. For example, defect targets may be covered by oil stains in the surface images of silicon steel sheets. These pseudo-defect interferences increase the accuracy of target detection and recognition. difficulty

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
  • An image detection method for surface defects of silicon steel plate under the interference of oil pollution
  • An image detection method for surface defects of silicon steel plate under the interference of oil pollution
  • An image detection method for surface defects of silicon steel plate under the interference of oil pollution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The specific implementation manners of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0038] An image detection method for surface defects of silicon steel sheets under oil pollution interference, such as figure 1 shown, including the following steps:

[0039] Step 1. Use an area array industrial camera to collect the surface defect image of the silicon steel plate;

[0040] Step 2, using a visual saliency method to detect defects on the collected silicon steel sheet surface defect images;

[0041] Step 2-1, using a 5×5 Gaussian filter window to filter the collected silicon steel plate surface defect image;

[0042] Step 2-2, performing color space conversion on the silicon steel plate surface defect image filtered in step 2-1 and the unfiltered silicon steel plate surface defect image, that is, from RGB color space to Lab color space;

[0043] Step 2-3, in the Lab color space, respectively calculate the avera...

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 silicon steel plate surface defect image detection method under oil pollution interference. The method comprises the following steps: acquiring a silicon steel plate surface defect image by using an area array industrial camera; performing defect detection on the acquired silicon steel plate surface defect image by using a visual salience method; performing positioning defection on the oil pollution defect image by using a salient line scanning morphology-based detection method. According to the method, the situation that a silicon steel plate is covered by oil pollution interferents is removed from the defect detection, and the difficulty of target detection and recognition is increased by the pseudo defect interference. The problems of disordered background during defect detection, oil pollution interference of coverage and pseudo defect interface of reflection are solved; line scanning filling operation is performed on a binary image in lack of information, and the operation can effectively obtain an oil pollution interference region; the oil pollution edge and the reflective pseudo defect edge are removed by applying an edge processing method of a morphology theory, and the problem that the pseudo edge cannot be effectively eliminated by subtraction operation is avoided.

Description

technical field [0001] The invention belongs to the technical field of machine vision and nondestructive testing, and in particular relates to an image detection method for surface defects of a silicon steel plate under the interference of oil pollution. Background technique [0002] Among metal sheets, silicon steel sheets are high-end steel products, and their manufacturing technology and product quality have become one of the important symbols to measure a country's special steel production and technological development level. Silicon steel plate, also known as silicon steel plate, is a silicon-iron soft magnetic alloy with extremely low carbon content, generally containing 0.5-4.5% silicon. It is mainly used to make iron cores of various generators, motors and transformers. At the same time, silicon steel plates are also indispensable and important soft magnetic alloy materials in electronics, electric power and military industries. Since the silicon steel plate is clos...

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): G06T7/00G06T5/30
CPCG06T7/0004G06T2207/30108G06T2207/30164
Inventor 宋克臣颜云辉董志鹏温馨赵永杰
Owner NORTHEASTERN UNIV LIAONING
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