Affiliation:
1. College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321000, China
2. School of Electronics and Information Engineering (School of Big Data Science), Taizhou University, Taizhou 318000, China
Abstract
Traditional identification methods for Papaver somniferum and Papaver rhoeas (PSPR) consume much time and labor, require strict experimental conditions, and usually cause damage to the plant. This work presents a novel method for fast, accurate, and nondestructive identification of PSPR. First, to fill the gap in the PSPR dataset, we construct a PSPR visible capsule image dataset. Second, we propose a modified MobileNetV3-Small network with transfer learning, and we solve the problem of low classification accuracy and slow model convergence due to the small number of PSPR capsule image samples. Experimental results demonstrate that the modified MobileNetV3-Small is effective for fast, accurate, and nondestructive PSPR classification.
Funder
National Natural Science Foundation of China
Zhejiang Province Public Welfare Technology Application Research Project
Subject
General Physics and Astronomy
Reference49 articles.
1. Identification of Papaver Somniferum L. and Papaver Rhoeas Using DSWT-FTIR-RBFNN;Zhang;Spectrosc. Spect. Anal.,2009
2. Species identification of Papaver by metabolite profiling;Choe;Forensic Sci. Int.,2011
3. Research of identification of papaver based on spectral analysis;Wang;Chin. J. Quantum Electron,2019
4. Li, Y.-Y. (2016). Construction and Application of a Fluorescent Complex Amplification System for Three Poppy SSR Motifs. [Master’s Thesis, Hebei Medical University]. (In Chinese).
5. Liu, X., Tian, Y., Yuan, C., Zhang, F., and Yang, G. (2018). Opium poppy detection using deep learning. Remote Sens., 10.
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献