| 基于深度残差学习的成熟草莓识别方法 |
| |
| 引用本文： | 张继成,李德顺.基于深度残差学习的成熟草莓识别方法[J].中国农机化学报,2022(2):136-142. |
| |
| 作者姓名： | 张继成 李德顺 |
| |
| 作者单位： | 长江大学工程技术学院;海南大学计算机科学与技术学院 |
| |
| 基金项目： | 湖北省教育厅科学技术研究项目(B2020340);长江大学工程技术学院科研基金项目(2020KY04)。 |
| |
| 摘 要： | 为解决自然状态下成熟草莓存在的背景干扰、信息丢失等问题,提出一种基于深度残差学习的草莓识别方法.首先,引入深度可分离卷积降低残差网络参数,从不同角度提取成熟草莓特征,通过交叉熵损失函数来识别分类层中的草莓.其次,嵌入压缩和激励模块学习特征权重,使用特征重新校准改善网络的学习和表征属性.最后,采用添加空间金字塔池化、加权...
|
| 关 键 词： | 草莓识别 深度可分离卷积 残差网络 深度学习 压缩和激励模块 数据增强 |
Ripe strawberry recognition method based on deep residual learning |
| |
| Zhang Jicheng,Li Deshun.Ripe strawberry recognition method based on deep residual learning[J].Chinese Agricultural Mechanization,2022(2):136-142. |
| |
| Authors: | Zhang Jicheng Li Deshun |
| |
| Institution: | (Yangtze University College of Technology&Engineering,Jingzhou,434020,China;School of Computer Science and Technology,Hainan University,Haikou,570228,China) |
| |
| Abstract: | To solve problems of background interference and information loss of ripe strawberries under natural state, a method for strawberry recognition was proposed based on deep residual learning in this study. Firstly, the depth-wise separable convolution was introduced to reduce the residual network parameters, the features of ripe strawberries were extracted from different aspects, and the strawberries in the classification layer were identified through the cross-entropy loss function. Additionally, the feature weights were learned by embedding compression and excitation modules, and feature recalibration was used to improve the learning and representation properties of the network. Finally, to further optimize the recognition results, the generalization ability of the model was improved by adding spatial pyramid pooling and weight decay optimization, which optimizes the recognition results. The experimental results demonstrate that compared with other current depth models, this method can effectively locate ripe strawberries under complex background and is not easily affected by the interference environment. With higher recognition accuracy and sensitivity, in data set C, the recognition accuracy and sensitivity are the highest, reaching 92.46% and 94.28%, respectively. |
| |
| Keywords: | strawberry recognition depth-wise separable convolution residual network deep learning squeeze-and-excitation blocks data to enhance |
| 本文献已被 维普 等数据库收录！ |
|
