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

Pear surface defect detection method based on machine vision

A machine vision, defect detection technology, applied in the direction of optical testing defects/defects, instruments, measuring devices, etc., can solve the problems of lax grading, rough packaging, reduced value and competitiveness, and achieve the effect of simple and easy-to-implement methods

Inactive Publication Date: 2014-12-17
JIANGNAN UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Sales situation that makes it difficult to adapt to market competition
In addition, the classification is not strict, the quality has no specifications, and the packaging is rough, which greatly reduces its value and competitiveness.

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
  • Pear surface defect detection method based on machine vision
  • Pear surface defect detection method based on machine vision
  • Pear surface defect detection method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] The collected images must firstly undergo certain preprocessing operations, including image conversion and image enhancement.

[0035] The image conversion of the collected color pear image includes: gray scale and RGB-HSI color space conversion. Color image, which contains a large amount of information, can extract a large amount of image information required by this topic, so as to achieve the purpose of defect identification. The grayscale image contains less information and cannot truly reflect and describe the objective reality, but it is precisely because of this feature that the grayscale image occupies less storage space and the amount of calculation for digital processing is small. Therefore, in image processing In the process, it is necessary to convert the color image into a grayscale image to facilitate processing and improve detection efficiency, such as figure 1 As shown in , it is the effect diagram after graying the three kinds of pears respectively.

...

Embodiment 2

[0041] The present invention adopts the segmentation method based on the template method when performing the background removal operation on the obtained pear image, and the flow chart is as follows Image 6 shown. The method is described as follows:

[0042] 1) Use the hardware equipment selected by design to shoot pears to obtain pear images with various defects;

[0043] 2) the pear image that is obtained is carried out preprocessing, has carried out analysis explanation in embodiment 1, has carried out gray scale and linear transformation;

[0044] 3) Perform binarization and denoising on the preprocessed image. The binarization and denoising processing here is to obtain a binary image with a black background and a white pear, so the morphological denoising used here The filter window can be made larger;

[0045] 4) Generate a background template and invert the logic of the binary image to obtain the template image. The template image is a binary image of the same size as...

Embodiment 3

[0051] After the background removal operation is performed, the defect is extracted on its I component, and the flow chart is as follows Figure 8 shown. The method is described as follows:

[0052] 1) extract the I component map from the pear image after removing the background, and carry out post-processing on it;

[0053] 2) Binarize the I component map. Here, the Otsu segmentation threshold method is used. The Otsu method chooses to maximize the variance between classes The threshold k of , the between-class variance is defined as

[0054] σ B 2 = w 0 ( u 0 + u T ) 2 + w 1 ( u 1 ...

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 pear surface defect detection method based on machine vision. Three varieties of pears are used as objects, and an appropriate mean detection is taken for completion of the pear surface defect detection task. The pear surface defect detection method comprises various kinds of pretreatment operation on collected pear images, after binaryzation, a morphological filtering method is used, a background removing method based on a template is firstly used in the pears; a background removed pear I component figure and a simple morphological addition method are used for defect extraction, in the process, an Otsu segmentation threshold method is chosen for binaryzation, and in order to meet the requirements of an automatic packaging line, the one-time property is adjusted in the method. The method can be used in defect extraction of a variety of pears, is universal, and plays the key role of ''eyes'' in the automatic packaging line.

Description

technical field [0001] The invention relates to a method for detecting fruit quality, in particular to a method for detecting fruit surface defects based on machine vision. Background technique [0002] China is a big agricultural country with the largest fruit output in the world, but the proportion of export is relatively small. One of the important reasons is that the post-harvest detection and grading technology of fruits is backward, and an advanced and effective grading system has not been established, which makes the quality of export fruit uneven. Unable to select high-quality fruits with consistent specifications, they lack competitiveness in the international market and cannot be placed on high-end shelves. [0003] The main reason for this situation is that the level of post-harvest treatment of agricultural products in our country is too low. 100% of the fruits in advanced countries need to be put on the market after post-harvest commercialization (cleaning, wa...

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): G01N21/88G01N21/952
Inventor 化春键周海英方程骏
Owner JIANGNAN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com