摘要
现阶段随着工业自动化的不断发展,实现草莓采摘的智能化、机械化已经成为了一种必然的发展趋势,而实现智能草莓采摘的关键就是要设计出精度较高的图像识别系统。本文中的图像识别系统在识别草莓的过程中采用了颜色识别和特征识别相结合的方法,两种方法的结果进行比对得到草莓的质心坐标并且分辨出成熟草莓与不成熟草莓,最终结果误差很小。同时我们加入了卷积神经网络辅助级联分类器来对目标物草莓进行判别,最终正确率可以达到92%以上。在此基础上,我们通过Python设计出上位机界面,界面中包含了图像识别效果图与控制指令等部分。
At current stage,with continuous development of industrial automation,it is an inevitable development trend to realize intelligentization and mechanization of strawberry picking,and the key to realize intelligent strawberry picking is to design a image recognition system with high precision.Image recognition system in the article adopts combining method of color and feature recognition during strawberry identifying process.Compare results of two methods to get centroid coordinates of strawberry and distinguish mature and immature strawberry,and final result is small.At the same time,we discriminate targeted strawberries with cascade classifier based on convolution neural network,and accuracy rate can reach more than 92%.On the basis,we designed host computer interface through Python,which includes image recognition effect diagram and control instruction and etc.
作者
侯贵洋
赵桂杰
王璐瑶
HOU Gui-yang;ZHAO Gui-jie;WANG Lu-yao(Department of Communications Engineering,Electronic Information Engineering School,Tianjin University of Technology,Xiqing,Tianjin,300387;Telecommunication Department,Electronic Information Engineering School,Tianjin University of Technology,Xiqing,Tianjin,300387;Eelectromechanical Department,Mechanical Engineering School,Tianjin University of Technology,Xiqing,Tianjin,300387)
出处
《软件》
2018年第6期184-188,共5页
Software
