Spectroscopy and Spectral Analysis, Volume. 42, Issue 11, 3626(2022)
Early Bruise Detection of Crystal Pear Based on Hyperspectral Imaging Technology and Transfer Learning
Figures & Tables(5)
Fig. 1. Schematic diagram of hyperspectral image acquisition system
Fig. 3. The first 8 PC images based on full-band PCA of slightly bruised samples
Fig. 4. Confusion matrix of each model for the identification of crush bruise time
Table 1. Recognition results using discriminant models using SVM, k-NN and ResNet50 for network transfer learning
View tableView in ArticleTable 1. Recognition results using discriminant models using SVM, k-NN and ResNet50 for network transfer learning
降维方法 模型 训练集 测试集 SVM 100% 83.33% PCA k-NN 100% 85.42% ResNet50 93.29% 93.75%
Tools
Get Citation
Copy Citation Text
Guang-lai WANG, En-feng WANG, Cong-cong WANG, Da-yang LIU. Early Bruise Detection of Crystal Pear Based on Hyperspectral Imaging Technology and Transfer Learning[J]. Spectroscopy and Spectral Analysis, 2022, 42(11): 3626
Paper Information
Category: Research Articles
Received: Aug. 30, 2021
Accepted: --
Published Online: Nov. 23, 2022
The Author Email: WANG Guang-lai (gellerwang@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20