Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A method for detecting surface defects of bamboo strips based on computer vision

A technology of computer vision and defect detection, which is applied in the field of image processing, can solve problems such as weak anti-noise ability, difficult to popularize and apply, and difficult to implement, and achieve the effect of strong anti-noise, simple and practical algorithm, and easy program implementation

Active Publication Date: 2017-09-01
GUANGXI NORMAL UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In industrial production, a large number of bamboo strips need to be detected. This method is difficult to implement and has low efficiency.
In addition, the stability of this method is not enough, and the anti-noise ability is weak. When the noise gradient is large and the gray value is low, this method will also misjudge the noise of a pixel as a defective bamboo strip.
Therefore this method is difficult to popularize and apply in bamboo product production

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
  • A method for detecting surface defects of bamboo strips based on computer vision
  • A method for detecting surface defects of bamboo strips based on computer vision
  • A method for detecting surface defects of bamboo strips based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] The main steps are as follows:

[0057] Ⅰ. Capture the image of the bamboo strips

[0058] Take the grayscale image f of the bamboo strip surface with black flannelette as the background, such as figure 2 As shown, there is a dark dot in the middle of the bamboo image;

[0059] Ⅱ. Normalization

[0060] The image f is normalized by the gamma correction method to obtain the image fg;

[0061] Ⅲ. Filtering

[0062] Perform median filtering and Gaussian filtering on image fg to obtain image f 1 ;

[0063] Ⅳ. Wavelet transform processing

[0064] Using sym4 wavelet to image f 1 Perform four-level wavelet transform to obtain image f 2 ,Such as image 3 As shown, the dark dots in the middle of the bamboo image are clearer;

[0065] Ⅴ. Threshold segmentation of the maximum between-class variance method

[0066] Using the maximum between-class variance method (OTSU) to image f 2 The foreground and background are thresholded, the segmentation threshold is t, and the...

Embodiment 2

[0076] The main steps are as follows:

[0077] Ⅰ. Capture the image of the bamboo strips

[0078] Identical with embodiment 1 step Ⅰ, the grayscale image f of the surface of the bamboo strips obtained is as follows Figure 7 As shown in , there is a light line on the edge of the bamboo strip image;

[0079] Steps II-IV are the same as in Example 1, and the image f is obtained 2 ,Such as Figure 8 As shown in , there is a light line on the edge of the bamboo strip image;

[0080] Step Ⅴ~same as embodiment 1, obtain image f 5 , this example image f 5 The area of ​​the defect connected domain displayed in is smaller than the defect domain area threshold A; judge that the bamboo strip has no mold spots or wormhole defects; enter step Ⅷ;

[0081] Ⅷ. Edge and crack detection

[0082] Use the canny operator to traverse the image f 2 , get the image f 6 ,Such as Figure 9 As shown, this image f 2 In addition to the crack defect, there is also the edge of the bamboo strip. ...

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 is a method for detecting defects on the surface of bamboo strips based on computer vision. The bamboo strip image is normalized, filtered and wavelet transformed; the maximum inter-class variance method is used to segment the image threshold, and the closed operation is used to fill the holes in the bamboo strip image, and then The negative effect of the closing operation is removed by the corrosion operation, and the wormhole and / or mildew defect in the bamboo strip image is segmented by the difference shadow method. If the area of ​​the connected domain of the defect is smaller than the threshold A of the defect domain area, it is considered that there is no mold or wormhole defect. , enter the crack detection; otherwise, calculate the average gray value Gm of the defective connected domain image, if the difference between Gm and the average gray value G0 of the bamboo strip image is greater than the threshold G, there will be mold spots or wormholes, and it will be judged as a defective bamboo strip; otherwise, detect edges and cracks, Remove the bamboo edge of the image, if the total number of non-zero pixels or the length of the maximum connected domain is greater than the corresponding threshold, and the average gray value of the crack is greater than G0, it is determined that there is a crack defect, otherwise it is qualified. The method has high detection efficiency, strong noise resistance and high stability, and the correct recognition rate reaches over 95%.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting surface defects of bamboo strips based on computer vision. Background technique [0002] my country is rich in bamboo resources and bamboo has a strong regeneration capacity. Bamboo has a smooth texture and clear texture, and is widely used in the manufacture of bamboo tapestries, bamboo carpets, bamboo floors and other architectural and decorative products. However, during the growth of bamboo, some insects, diseases or decay are unavoidable. The intermediate product bamboo strips made, due to reasons such as various environmental climates and humidity, some bamboo strips will crack during processing and storage, and some bamboo strips will become moldy. Therefore, defects such as insect-eaten holes, cracks, and mildew spots often appear on the surface of bamboo strips. Before the next step of bamboo product processing, the surface defects of b...

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): G01N21/88G01N21/95G06T3/00G06T5/00
Inventor 夏海英宋树祥李建辉周祚山牟向伟
Owner GUANGXI NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products