Round fruit picking system based on machine vision
Year: 2024
Type: conference-paper
Abstract: Traditional fruit quality selection mainly relies on manual labor, which is costly and time-consuming, and the results are difficult to meet the accuracy requirements. To solve this problem, this paper proposes a fruit-picking system based on machine vision technology using MATLAB as a software tool. It takes round fruits as the research object, introducing Zhang’s camera calibration method, making the target picture reach the ideal state through image pre-processing, such as edging processing, filtering and denoising, binary processing, size eigenvalue extraction, etc. Then, the fruit size grade is evaluated by using the Sobel edge detection algorithm. The fruit color grade is evaluated using the HSV detection algorithm to assess the fruit color grade, and a feature extraction method is used to assess the relative score of the defect degree. Finally, a weighted composite score is used to evaluate the fruit quality grade. This paper also designed a visualized GUI interface. The results prove that the system can accurately and quickly perform fruit selection and quality rating.
Authors: Xiumei Fang, Haiyang Zhu, Sanyan Li, Qilong Zhang
Institution: Chengdu Jincheng College
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W4405284183