Classification of Camellia species from 3 sections using leaf anatomical data with back-propagation neural networks and support vector machines

Abstract

Leaf characteristics provide many useful clues for taxonomy. We used a back-propagation artificial neural network (BPANN) and C-support vector machines (C-SVMs) to classify 47 species from 3 sections of genus Camellia (16 from sect. Chrysanthae, 16 from sect. Tuberculata, and 15 from sect. Paracamellia). The classification model was constructed based on 7 leaf anatomy attributes including, area of adaxial epidermal cell, thickness of adaxial epidermal cell, thickness of palisade parenchyma, thickness of total leaf, thickness of spongy parenchyma, thickness of abaxial epidermal cell, and area of abaxial epidermal cell. Model parameters of C-SVM, comprising regularization parameter (C) and kernel parameter (γ), were optimized by cross-validation. The best classification accuracy of the 3 Camellia sections was achieved by the radial basis function SVM classifier (with parameters C = 32, γ = 0.13), as well as the sigmoid SVM classifier (with parameters C = 32, γ = 0.13), which was up to 84.00% in the training set and 90.91% in the prediction set, respectively. Compared with BP-ANN, SVM yields slightly higher prediction accuracy, which indicates that it is feasible to accurately classify the 3 sections of Camellia using SVMs based on leaf anatomy data. © TÜBİTAK

Leaf morphology and shoot regeneration of in vitro cultured explants from species of the Solanum peruvianum s.l. complex

“…Several traits related to leaves are commonly used in taxonomic classification Jiang et al, 2013). In our assay, we showed interspecific and intraspecific variability for leaf morphology and the species can be differentiated by number of leaflets or by leaflet margin dentation.…”

Morphological, physicochemical, and phytochemical characterization of Camellia dormoyana (Pierre) Sealy from Vietnam

“…Leaf structure such as the pattern and size of epidermal cells, the layer of the epidermal cell, the thickness of palisade tissue and spongy tissue, and stomata characteristics were significant taxonomic tools for identifying species (Lu et al 2012;Jiang et al 2013;Qi et al 2017). The leaves show a thick cuticle in C. dormoyana, similar to other Camellia species, such as C. sinensis, C. assmica subsp.…”

Leaf Image Classification Based on Pre-trained Convolutional Neural Network Models

“…When leaf similarities are NESciences, 2023, 8 (3): 214-232 doi: 10.28978/nesciences.1405175 taken into account, if people do not have expertise, they cannot be expected to have detailed knowledge about these plants. There is a known fact that leaf characteristics provide many useful clues for taxonomy of the leaf (Jiang et al, 2013). With technological developments, it is possible to produce solutions or improve such problems.…”

“…In addition, There are studies in which classification is made with different methods using feature vectors extracted from the trained convolutional neural network called pre-trained models (Lee et al, 2017;Beikmohammadi & Faez, 2018;Wang et al, 2018;Raj & Va jravelu, 2019). Different classification methods such as logistic regression (LR) , support vector machine (SVM), Naive Bayesian, linear discriminant analysis (LDA), radial fundamental probabilistic neural network (RF-PNN), multilayer perceptron (MP), AdaBoost, probabilistic neural network have been used (Silva et al, 2013;Jiang et al 2013;Padao & Maravillas, 2015;Mostafa et al, 2020;Sujith & Neethu, 2021).…”