Research and implementation of the non-destructive sorting system for full surface information of jujube based on machine vision technology
CSTR:
Author:
Affiliation:

(1. School of Electromechanical Engineering, Guangdong Bai yun University, Guangzhou, Guangdong 510450, China; 2. Guangdong Face Intelligence Technology Co., Ltd, Guangzhou, Guangdong 510507, China)

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Based on machine vision technology, a non-destructive sorting system for full surface information of jujube is designed. The whole machine consists of several parts, including automatic feeding mechanism, sorting mechanism, conveying and attitude adjustment mechanism, grading actuator, detecting and controlling part. Based on theory of mirror reflection principle, an inspection mechanism that can provide the full surface information to the Image processing software is designed to capture a top image, a bottom image and two side images of jujube at the same time, then the problem that the previous sorting system cannot acquire a whole surface information of the red jujube in the condition of high speed transportation is solved. The grading software is designed to process the acquired images in real time, and obtains the surface information such as fruit shape, surface quality and texture. Finally, information fusion technology is used to sort the red jujube with the surface information. The test result shows that the sorting speed of this system is fast, and the sorting accuracy is more than 90%. It can meet the production requirements of detecting and sorting jujube rapidly in an automated way.

    Reference
    Related
    Cited by
Get Citation

钟小华,曹玉华,张永清,等.基于机器视觉技术的红枣全表面信息无损分拣系统研究与实现[J].食品与机械英文版,2017,33(5):114-118.

Copy
Related Videos

Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:
  • Revised:
  • Adopted:
  • Online: March 10,2023
  • Published:
Article QR Code