Fruit surface defect detection method based on image marking
A defect detection and image marking technology, which is applied in the direction of optical defect/defect testing, measuring devices, and material analysis through optical means, can solve problems such as insufficient practicability, reduce labor intensity and error rate, and improve production efficiency Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0038] Example one
[0039] The present invention is a method for detecting fruit surface defects based on image marking, taking first-class apples (without defects) as an example as the object to be tested, see figure 1 , 2 , Including the following steps:
[0040] 1) The user uses the image acquisition device to take a picture of the surface of the apple to be tested on the spot and save it to obtain the original image;
[0041] 2) The user uploads the original image to be detected to the Apple surface defect detection server through wireless or wired means, and the server analyzes the original image and outputs the result;
[0042] Such as figure 1 As shown, the processing steps of the server include:
[0043] a. Convert the acquired original image from the RGB space to the human visual system, use Hue, Saturation and Intensity to describe the HSI color space of the color, and extract the H and I components ;
[0044] b. Use OSTU maximum between-class variance method for dynamic th...
Example Embodiment
[0066] Example two
[0067] Take an apple with two defects on its surface as an example as the test object, see figure 1 , 2 , Including the following steps:
[0068] 1) The user uses the image acquisition device to take a picture of the surface of the apple to be inspected on the spot and save it to obtain the original image;
[0069] 2) The user uploads the original image to be detected to the Apple surface defect detection server through wireless or wired means, and the server analyzes the original image and outputs the result;
[0070] Such as figure 1 As shown, the processing steps of the server include:
[0071] a. Convert the acquired original image from the RGB space to the HSI color space of the human visual system, using Hue, Saturation and Intensity to describe the HSI color space, and extract the H and I components ;
[0072] b. Use OSTU maximum between-class variance method for dynamic threshold segmentation of H component;
[0073] c. Perform statistics on the gray-scale ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap