Identification of Disease Type of Tobacco Leaves Based on Near Infrared Spectroscopy and Convolutional Neural Network

• DOI: 10.21577/0103-5053.20230181
• Publication Date: 2023-11-10T12:10:28Z
• Authors: Liang Ying; Ma Kun; Zhang Xinyu; Yang Qifu; Wu Jiaquan; Yang Shuangyan
• Keywords: Identification

It is important to identify the types of tobacco diseases accurately and take effective control measures in time improve efficiency planting. In this paper, a hand-held nearinfrared spectrometer was used collect spectral data different disease samples. The training models were established via convolutional neural network algorithm. Meanwhile, traditional classification algorithms support vector machine back propagation also compared. results showed that prediction accuracy algorithm highest overall performance model best. rapid detection method based on near-infrared could leaf species efficiently, non-destructively, quickly accurately, which provided new technical reference for identification.