摘要
我国苹果种植面积广、产量大,但是传统人工分级很难满足现代生产要求,提高苹果分级效率急需自动化的机械分级系统。基于树莓派平台,设计并实现了一种小型的嵌入式苹果分级系统。该系统通过采集苹果图像,利用单阈值分割和Canny算子完成图像分割和图像边缘提取。利用机器学习领域的BP神经网络算法实现分级。实验结果表明,该系统实时性和准确度都较高,基本满足自动化分级的要求。
The Apple planting area is wide and the yield is large in China,but the traditional manual grading is difficult to meet the requirements of modern production,so the automatic mechanical grading system is urgently needed to improve apple grading efficiency.This paper designs a small embedded apple grading system based on raspberry pi platform.The system is used to collect apple images,then,single threshold segmentation and Canny operator are used to complete the image segmentation and the image edge extraction.The BP neural network algorithm in machine learning field is used to realize the classification.The experimental results show that the system has high real-time performance and accuracy,and basically meets the requirements of the automatic classification.
作者
李彬
胡步发
刘顾胜
LI Bin;HU Bufa;LIU Gusheng(College of Mechanical Engineering and Automation,Fuzhou University,Fuzhou 350116,China)
出处
《机械制造与自动化》
2020年第4期209-211,共3页
Machine Building & Automation
