| 融合整体与局部信息的武夷岩茶叶片分类方法 |
| |
| 引用本文： | 林丽惠,,罗志明,,王军政,李绍滋.融合整体与局部信息的武夷岩茶叶片分类方法[J].智能系统学报,2020,15(5):919-924. |
| |
| 作者姓名： | 林丽惠 罗志明 王军政 李绍滋 |
| |
| 作者单位： | 1. 武夷学院 数学与计算机学院，福建 武夷山 354300;2. 武夷学院 认知计算与智能信息处理福建省高校重点实验室，福建 武夷山 354300;3. 厦门大学 信息与通信工程博士后流动站，福建 厦门 361005;4. 厦门大学 信息科学与技术学院，福建 厦门 361005 |
| |
| 摘 要： | 针对武夷岩茶鲜茶叶叶片图像分类问题，提出一种融合整体与局部信息的分类方法。该方法使用两分支并行结构构建了一个整体与局部信息融合的卷积神经网络模型。实验表明，在9个品种共计7330张武夷岩茶鲜茶叶叶片图像数据集上，基于ResNet18构造的两分支并行卷积神经网络模型的分类准确率为96.68%，超过了其他CNN模型的分类准确率。这表明通过融合全局信息、边缘形状信息和纹理局部信息能有效提高分类准确率。
|
| 关 键 词： | 武夷岩茶叶片分类 深度学习 迁移学习 特征融合 卷积神经网络 残差网络 边缘形状 纹理 |
Classification of Wuyi rock tealeaves by integrating global and local information |
| |
| LIN Lihui,,LUO Zhiming,,WANG Junzheng,LI Shaozi.Classification of Wuyi rock tealeaves by integrating global and local information[J].CAAL Transactions on Intelligent Systems,2020,15(5):919-924. |
| |
| Authors: | LIN Lihui LUO Zhiming WANG Junzheng LI Shaozi |
| |
| Affiliation: | 1. School of Mathematics and Computer Science, Wuyi University, Wuyishan 354300, China;2. The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions, Wuyi University, Wuyishan 354300, China;3. Post-Doctoral Mobile Station of Information and Communication Engineering, Xiamen University, Xiamen 361005, China;4. Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen 361005, China |
| |
| Abstract: | In this study, we focused on the classification of fresh Wuyi rock tealeaf images into different fine-grained categories and the construction of a two-branch parallel-structured convolutional neural network (CNN) model by integrating global and local information. We constructed a Wuyi rock tealeaf image dataset comprising 7330 fresh tealeaf images of nine varieties. The experimental results showed that the proposed two-branch parallel-structured CNN model with ResNet18 achieved an accuracy of 96.68% on the Wuyi rock tealeaf image dataset, which is superior to that of other CNN models. This result demonstrates that integrating global information and local information relating to edge shape and texture can effectively improve classification accuracy. |
| |
| Keywords: | classification of Wuyi rock tealeaves deep learning transfer learning feature integration convolutional neural network residual network edge shape texture |
|
| 点击此处可从《智能系统学报》浏览原始摘要信息 |
|
点击此处可从《智能系统学报》下载全文 |
|
