首页|基于坐标注意力机制和残差网络的苹果外观品质检测

基于坐标注意力机制和残差网络的苹果外观品质检测

扫码查看
随着机器视觉技术的发展,利用卷积神经网络实现苹果品质分级已成为较优的应用技术.本研究以苹果外观品质特征为对象,提出了一种基于残差神经网络和坐标注意力机制的苹果品质检测方法.实验结果显示,引入坐标注意力机制后的ResNet18 网络模型平均准确率达到 91.4%,损失值为 0.1.该方法在各项性能上优于ResNet18、34、50 网络模型,能够有效实现苹果品质分级.
Apple Appearance Quality Detection Based on Coordinate Attention Mechanism and Residual Network
With the development of machine vision technology,the use of convolutional neural network to achieve apple quality classification has become a better technology.In this paper,an apple quality detection method based on residual neural network and coordinate attention mechanism is proposed.The experimental results show that the average accuracy of ResNet18 network model after the introduction of coordinate attention mechanism reaches 91.4%,and the loss value is 0.1.This method has better performance than ResNet18,34 and 50 network models,and can effectively realize Apple quality classification.

coordinate attention mechanismresidual neural networkmachine visionfruit classification

齐永兰、李仁惠、李学伟

展开 >

河南工学院智能工程学院,河南 新乡 453000

坐标注意力机制 残差神经网络 机器视觉 水果分级

2024

现代食品
国家粮食储备局郑州科学研究设计院

现代食品

影响因子:0.169
ISSN:2096-5060
年,卷(期):2024.30(10)
  • 3