Intelligent defect detection method for milk outer package

CN119067923AActive Publication Date: 2024-12-03INST OF ANIMAL SCI & VETERINARY MEDICINE SHANDONG ACADEMY OF AGRI SCI +1

Patent Information

Application Number
CN202411083204.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-12-03
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

When detecting the defects of the outer packaging of milk, due to the texture interference of the glass bottle, the detection accuracy and efficiency are low, making it difficult to effectively identify the defects of the bottled milk.

Method used

By obtaining the grayscale image at the bottom of the bottle, threshold segmentation and edge chain code sequence analysis are performed, combined with the grayscale uniformity and gradient information of the 8-neighborhood of the pixel points, the target area is selected, and the defects are further determined through morphological operations and high-light screening. Area, determine whether the outer packaging of the bottle bottom is qualified.

Benefits of technology

It improves the accuracy and efficiency of the detection of defects in milk outer packaging, reduces the lack of detailed information, and ensures accurate identification of defects in bottled milk.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067923A_ABST
    Figure CN119067923A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of image processing, in particular to an intelligent defect detection method for a milk outer package, which comprises the following steps of: acquiring a bottle bottom grayscale image and obtaining a suspected region, calculating 8-neighborhood grayscale uniformity of each pixel point of the bottle bottom grayscale image, and further screening out a target region; screening out a plurality of highlight points in each target area, screening out a plurality of defect areas in all the target areas according to 8 neighborhood gray level uniformity and gradient of the highlight points and surrounding pixel points, finding out missing defect areas according to defect area characteristics, and finding out missing defect areas according to position distribution of all the defect areas in the bottle bottom gray level image. And judging whether the outer package at the bottom of the bottle is qualified or not. According to the method, interference information is screened according to the gray difference and the edge features between the areas, and finally the defect area is determined, so that the accuracy and the efficiency of identifying the defects of the bottled milk outer package in the prior art are effectively improved, and the loss of detail information is reduced.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Integrated circuit wafer surface defect detection method based on artificial intelligence

    CN115035122A

  • Hard carbon electrode production quality detection method

    CN116843678A

  • Visual detection method and system for surface defects of battery cover plate

    CN117152129A

  • Paper product printing defect detection method

    CN117541588A

  • Plastic mold production defect detection method based on image processing

    CN117611563A

Cited By

  • Dynamic weighing and visual inspection system for sea-buckthorn juice filling production line

    CN120876403A