| 基于低秩自动编码器及高光谱图像的茶叶品种鉴别 |
| |
| 引用本文： | 孙俊,靳海涛,武小红,陆虎,沈继锋,戴春霞.基于低秩自动编码器及高光谱图像的茶叶品种鉴别[J].农业机械学报,2018,49(8):316-323. |
| |
| 作者姓名： | 孙俊 靳海涛 武小红 陆虎 沈继锋 戴春霞 |
| |
| 作者单位： | 江苏大学电气信息工程学院;江苏大学计算机科学与通信工程学院 |
| |
| 基金项目： | 国家自然科学基金项目（31471413）、江苏高校优势学科建设工程项目（苏政办发（2011）6号）、江苏省六大人才高峰项目（ZBZZ-019）和江苏大学大学生科研立项项目（Y15A038） |
| |
| 摘 要： | 提出一种基于低秩自动编码器及高光谱图像技术的茶叶品种鉴别方法。应用高光谱成像系统采集5个品种的茶叶样本高光谱图像数据,利用ENVI软件确定高光谱图像的感兴趣区域(ROI),并提取茶叶样本在ROI的平均光谱作为该样本的原始光谱数据。由于高光谱信息量大、冗余性强且存在噪声,运用自动编码器和低秩矩阵恢复结合的低秩自动编码器(LR-SAE)对原始光谱数据进行降维,在自动编码器降维基础上加入去噪处理,提取鲁棒判别特征。在此基础上应用支持向量机(SVM)和Softmax分类算法对降维后的茶叶样本高光谱数据分类。通过5折交叉试验验证,LR-SAE-SVM模型的预测集准确率达到99.37%,SAE-SVM模型的预测集准确率为98.82%;LR-SAE-Softmax模型的预测集准确率达99.04%,SAE-Softmax模型的预测集准确率为97.99%。研究结果表明,相较于未进行去噪处理的传统自动编码器,LR-SAE降维之后的分类建模效果有所提升,将其应用于茶叶品种鉴别是可行、高效的。
|
| 关 键 词： | 茶叶 品种鉴别 自动编码器 低秩矩阵恢复 高光谱 降维 |
| 收稿时间： | 2018/2/25 0:00:00 |
Tea Variety Identification Based on Low-rank Stacked Auto-encoder and Hyperspectral Image |
| |
| SUN Jun,JIN Haitao,WU Xiaohong,LU Hu,SHEN Jifeng and DAI Chunxia.Tea Variety Identification Based on Low-rank Stacked Auto-encoder and Hyperspectral Image[J].Transactions of the Chinese Society of Agricultural Machinery,2018,49(8):316-323. |
| |
| Authors: | SUN Jun JIN Haitao WU Xiaohong LU Hu SHEN Jifeng and DAI Chunxia |
| |
| Institution: | Jiangsu University,Jiangsu University,Jiangsu University,Jiangsu University,Jiangsu University and Jiangsu University |
| |
| Abstract: | Five different varieties of tea samples were classified with the method combining stacked auto-encoder (SAE) with low-rank matrix recovery (LRMR). The hyperspectral imaging system with spectrum range of 431~962 nm was used to collect five kinds of tea samples containing 618 bands of hyperspectral images, including Huangshan green tea, Longjing, Yixing Mao Feng, Yunwu green tea and Biluochun. The ENVI software was used to determine the region of interest (ROI) of the hyperspectral images, and the average spectral data of the sample in ROI were extracted as the raw spectral information of the sample. Due to the large amount, strong redundancy and much noise of the hyperspectral information, the low-rank stacked auto encoder (LR-SAE), which combined the stacked auto-encoder and the low-rank matrix recovery, was used to reduce the dimensionality of the hyperspectral data of the tea samples. Support vector machine (SVM) and Softmax classification model were applied to identify the tea samples after dimensionality reduction. The 5-fold cross validation experiment results showed that the accuracy of prediction set of LR-SAE-SVM model was 99.37%, and that of SAE-SVM model was 98.82%. As for Softmax classification, the accuracy of prediction set of LR-SAE-Softmax model was 99.04%, and that of SAE-Softmax model was 97.99%. The results showed that the accuracy of the classification model based on LR SAE was improved on some degree and the LR SAE had better robustness than the traditional SAE without de noising. It was feasible and efficient to apply the classification model based on LR-SAE into tea variety identification. |
| |
| Keywords: | tea variety identification stacked auto-encoder low-rank matrix recovery hyperspectral dimensionality reduction |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《农业机械学报》浏览原始摘要信息 |
| 点击此处可从《农业机械学报》下载免费的PDF全文 |
|
