Spyder 3

The Fritillaria samples in the hyperspectral images were cropped from irrelevant backgrounds using ENVI 4.6 (ITT Visual Information Solutions, Boulder, CO, USA). Hyperspectral images were extracted and pre-processed using MATLAB R2018a (The MathWorks, Natick, MA, USA). MATLAB R2018a was also used to implement PCA for pattern recognition between different varieties. Spyder 3.2.6 (Anaconda, Austin, TX, USA) was used to implement Python-based discriminant models, including SVM, PLS-DA, and CNN. Programming was conducted with scikit-learn (http://scikit-learn.org/stable/, accessed on 22 August 2022) and Pytorch (Facebook, Menlo Park, CA, USA). An Intel(R) core (TM) i5-8500 processor with 3.00 GHz and 8G RAM was used as the hardware platform for the execution of all software tools.

ENVI 4.6 (ITT Visual Information Solutions, Boulder, CO, USA) was used to crop the Chrysanthemum samples from the irrelevant background in hyperspectral images. MATLAB R2018a (The MathWorks, Natick, MA, USA) was used to extract and preprocess the spectral data from hyperspectral images. PCA for pattern recognition between different varieties was also implemented with MATLAB R2018a. Unscrambler 10.1 (CAMO AS, Oslo, Norway) was used to extract the optimal wavelengths by 2nd derivative method. Discriminant models including SVM, LR and DCNN were implemented using python language with Spyder3.2.6 (Anaconda, Austin, TX, USA). The famous machine learning library sklearn (http://scikit-learn.org/stable/) and convenient deep learning framework Pytorch (Facebook, Menlo Park, CA, USA) were used during programming. All software tools were carried out on the software platform of win10 64-bit operating system and the hardware platform of a computer with Inter(R) Core (TM) i5-8500 3.00 HZ CPU and 8 G memory.