基于机器视觉的谷糙分界线检测方法  

Paddy-brown rice boundary detection method based on machine vision

作　　者：刘浩 范吉军 余南辉 刘晓鹏 周劲 牟怿 LIU Hao;FAN Jijun;YU Nanhui;LIU Xiaopeng;ZHOU Jin;MOU Yi(School of Electrical and Electronic Engineering,Wuhan Polytechnic University,Wuhan,Hubei 430023,China;School of Mechanical Engineering,Wuhan Polytechnic University,Wuhan,Hubei 430023,China)

机构地区：[1]武汉轻工大学电气与电子工程学院,湖北武汉430023 [2]武汉轻工大学机械工程学院,湖北武汉430023

出　　处：《食品与机械》2024年第1期108-114,共7页Food and Machinery

基　　金：湖北省重点研发计划(编号:2023BBB018);湖北省重点研发计划(编号:2022BBA0047);湖北省技术创新专项(编号:2022BEC054)。

摘　　要：目的:精准识别谷糙分界线。方法:提出一种基于直线边缘检测的谷糙分界线识别方法。该方法对不同颜色特征的谷糙分离图像进行模型匹配,将不同匹配结果的图像采用对应的灰度化处理方式;并利用直线边缘检测算法对该边缘进行灰度波动变换、差分处理得到目标位置。结果:相较于传统的边缘检测方法,该方法将误差范围控制在5%以内,大幅提高了识别精度。结论:该方法的识别误差相对较小,适合用于谷糙分界线的识别应用。Objective:To detect and locate the boundary line between paddy and brown rice in separation equipment.Methods:A method based on straight-line edge detection was proposed by performing model matching with different color features.Converted the resulting images to grayscale and applied the linear edge detection algorithm to locate the target position.Results:Our approach reduced the error to within 5%and significantly improved recognition accuracy compared to traditional methods.Conclusion:Proposed method has a small recognition error,making it suitable for identifying the boundary between paddy and brown rice.

关 键 词：分界线 谷糙分离 边缘检测 机器视觉 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TS210.7[自动化与计算机技术—计算机科学与技术]