基于OpenCV的木材表面缺陷检测系统设计与实验验证  

Design and Experimental Study of Wood Surface Defect Detection System Based on OpenCV

作　　者：张发军 明晓杭 宋钰青 邓安禄 ZHANG Fajun;MING Xiaohang;SONG Yuqing;DENG Anlu(Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance,Yichang 443002,China;College of Mechanical and Power,China Three Gorges University,Yichang 443002,China)

机构地区：[1]水电机械设备设计与维护湖北省重点实验室,湖北宜昌443002 [2]三峡大学机械与动力学院,湖北宜昌443002

出　　处：《机械工程师》2019年第1期21-23,30,共4页Mechanical Engineer

基　　金：国家自然科学基金项目(51275273);水电机械设备设计与维护湖北省重点实验室开放基金项目(2017KJX02)

摘　　要：为解决在木材加工过程中木材表面缺陷检测环节的人工操作效率低下、检测质量不稳定等问题,采用基于OpenCV的计算机视觉技术,设计了一套木材表面缺陷自动检测系统。该系统能够检测出木板表面有无缺陷,并给出相应标记以方便进行后续加工。最后设计实验验证了该系统的图像识别能力,测得识别准确率达到95.3%,平均识别时间0.361s。实验结果表明该木材表面缺陷检测系统性能达到并超过了人工检测能力。In order to solve the problems of low manual operation efficiency and unstable detection quality in the wood surface defect detection process in wood processing,a set of automatic detection system for wood surface defects was designed by using OpenCV-based computer vision technology.The system is capable of detecting the presence or absence of defects on the surface of the board and giving corresponding markings to facilitate subsequent processing.Finally,the design experiment verifies the image recognition ability of the system.The testing accuracy is 95.3% and the average testing time is 0.361 second.The experimental results show that the performance of the wood surface defect detection system meets and exceeds the manual detection.

关 键 词：木材加工 表面缺陷 计算机视觉 自动检测 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]