摘要
目的:实现白酒酒花自动分类,提高摘酒的实时性与稳定性。方法:提出以机器视觉结合卷积神经网络代替人眼进行摘酒的方法,并与多种图像分类方法进行比较,验证改进分类算法的优越性。结果:基于改进Vgg16卷积神经网络+迁移学习方法分类模型准确率高达96.69%。结论:该方法能够实时稳定地对白酒酒花进行分类。
Objective:This study focuses on realizing the automatic classification of liquor flowers and then improving the real-time and stability of liquor picking.Methods:The machine vision combined with convolutional neural network was used to replace human eyes for liquor picking.Comparing with many image classification methods,the superiority of the improved algorithm was verified.Results:The results showed that the classification accuracy of the model based on the improved Vgg16 convolutional neural network plus transferring-learning method was up to 96.69%.Conclusion:This method can be used in the real-time classification of Baijiu hops stably.
作者
潘斌
韩强
姚娅川
PAN Bin;HAN Qiang;YAO Ya-chuan(School of Automation and Information Engineering,Sichuan University of Science&Engineering,Zigong,Sichuan 643000,China;Sichuan Key Laboratory of Artificial Intelligence,Sichuan University of Science&Engineering,Zigong,Sichuan 643000,China;School of Physics and Electrical Engineering,Sichuan University of Science&Engineering,Zigong,Sichuan 643000,China)
出处
《食品与机械》
北大核心
2021年第10期30-37,88,共9页
Food and Machinery
基金
四川省科技厅项目(编号:2021YFS0339)
四川省重大科技专项项目(编号:2018GZDZX0045)。
关键词
白酒
酒花
机器视觉
图像分类
卷积神经网络
baijiu
hops
machine vision
image classification
convolution neural network
