机器视觉在物料识别分拣中的应用  

Application of machine vision in material identification and sorting

作　　者：任娟娟[1] 冯中强 REN Juanjuan;FENG Zhongqiang(School of Commercial and Trade Circulation,Polytechnic Institute,Xianyang 712000,Shaanxi,China;School of Mechanical and Electrical Engineering, Xi’an Polytechnic University, Xi’an 710048,China)

机构地区：[1]陕西工业职业技术学院商贸与流通学院,陕西咸阳712000 [2]西安工程大学机电工程学院,陕西西安710048

出　　处：《西安工程大学学报》2021年第4期90-94,101,共6页Journal of Xi’an Polytechnic University

基　　金：国家重点研发计划项目(2019YFB1707205);陕西省中华职业教育社2021年职业教育研究课题(ZJS202106)。

摘　　要：为了提高物料分拣效率、降低成本,设计了一种基于机器视觉的物料识别、定位、抓取系统,系统包括物料传送、识别、定位、控制和分拣等单元。通过双边滤波的图像预处理、图像边缘检测以及图像特征提取等方法完成机器视觉的物料识别,并以螺母和螺栓为例进行实验验证。结果表明:物料识别的正确率为99.35%,分拣成功率能达到99.25%。所采用的物料识别和分拣方法具有识别率高、分拣准确等特点,提高了分拣系统的自适应性,能够满足物料分拣的要求。In order to improve the efficiency and reduce the cost in the process of material sorting material identification,positioning and grabbing system based on machine vision was designed,including material transfer unit,material identification and positioning unit,control unit,and material sorting unit.The material identification based on machine vision was realized by bilateral filtering,image edge detection,image feature extraction,image processing algorithms.And by taking boit and nut as example,the experimental verification carried out.The experimental results show that the correct rate of material identification can reach 99.35%,and the success rate of sorting can reach 99.25%.The material identification and sorting method has the characteristics of high identification rate and accurate sorting,which improves the adaptability of the sorting system and meets the requirements of material sorting.

关 键 词：物料分拣 机器视觉 边缘提取 特征识别 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]