Zhong Qiongda, Zhang Hu, Tang Shuqi, Li Peng, Lin Caixia, Zhang Ling, Zhong Nan
College of Engineering, South China Agricultural University, Guangzhou 510642, China.
Heyuan Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Heyuan 517000, China.
Foods. 2023 May 22;12(10):2089. doi: 10.3390/foods12102089.
The rapid detection of chestnut quality is a critical aspect of chestnut processing. However, traditional imaging methods pose a challenge for chestnut-quality detection due to the absence of visible epidermis symptoms. This study aims to develop a quick and efficient detection method using hyperspectral imaging (HSI, 935-1720 nm) and deep learning modeling for qualitative and quantitative identification of chestnut quality. Firstly, we used principal component analysis (PCA) to visualize the qualitative analysis of chestnut quality, followed by the application of three pre-processing methods to the spectra. To compare the accuracy of different models for chestnut-quality detection, traditional machine learning models and deep learning models were constructed. Results showed that deep learning models were more accurate, with FD-LSTM achieving the highest accuracy of 99.72%. Moreover, the study identified important wavelengths for chestnut-quality detection at around 1000, 1400 and 1600 nm, to improve the efficiency of the model. The FD-UVE-CNN model achieved the highest accuracy of 97.33% after incorporating the important wavelength identification process. By using the important wavelengths as input for the deep learning network model, recognition time decreased on average by 39 s. After a comprehensive analysis, FD-UVE-CNN was deter-mined to be the most effective model for chestnut-quality detection. This study suggests that deep learning combined with HSI has potential for chestnut-quality detection, and the results are encouraging.
板栗品质的快速检测是板栗加工中的一个关键环节。然而，由于缺乏可见的表皮症状，传统成像方法在板栗品质检测方面面临挑战。本研究旨在开发一种快速高效的检测方法，利用高光谱成像（HSI，935 - 1720 nm）和深度学习建模对板栗品质进行定性和定量识别。首先，我们使用主成分分析（PCA）对板栗品质进行定性分析可视化，随后对光谱应用三种预处理方法。为比较不同模型对板栗品质检测的准确性，构建了传统机器学习模型和深度学习模型。结果表明，深度学习模型更准确，FD - LSTM的准确率最高，达到99.72%。此外，该研究确定了板栗品质检测的重要波长在1000、1400和1600 nm左右，以提高模型效率。在纳入重要波长识别过程后，FD - UVE - CNN模型的准确率最高，达到97.33%。通过将重要波长作为深度学习网络模型的输入，识别时间平均减少了39秒。综合分析后，确定FD - UVE - CNN是板栗品质检测最有效的模型。本研究表明，深度学习与HSI相结合在板栗品质检测方面具有潜力，结果令人鼓舞。
