Table 1. Plant recognition studies based on traditional methods.

Researchers	Feature extraction methods	Classification methods	Datasets	Accuracy score (%)
Wu et al. (2007)	Shape features	Probabilistic Neural Network (PNN)	Flavia	90.00
Silva, Marcal & Silva (2013)	Shape features	Linear Discriminant Analysis (LDA)	ICL	87.00
Naresh & Nagendraswamy (2016)	Improved Local Binary Pattern (LBP)	k-Nearest Neighbors (k-NN)	Flavia	97.55
			Swedish	96.83
			Foliage	90.62
Tsolakidis, Kosmopoulos & Papadourakis (2014)	Zernike Moment & histogram of oriented gradients (HOG)	Support Vector Machine (SVM)	Flavia	97.18
			Swedish	98.13
Kadir et al. (2012)	Shape, color, texture features & PCA	PNN	Flavia	95.00
			Foliage	93.75
Elhariri, El-Bendary & Hassanien (2014))	Shape, color & texture features	LDA	ICL	92.65
Wang, Liang & Guo (2014)	Dual-scale decomposition & local binary descriptors	k-NN	Flavia	99.25
			ICL	98.03
Saleem et al. (2019)	Shape & texture features	k-NN	Flavia	98.75
Munisami et al. (2015)	Shape & color features	k-NN	Folio	87.30
Ren, Wang & Zhao (2012)	Multi-scale overlapped block LBP	SVM	Swedish	96.67
Sulc & Matas (2015)	Rotation & scale invariant descriptor based on LBP	SVM	Flavia	99.50
			Foliage	99.00
			Swedish	99.80
			Folio	99.20
Qi et al. (2014)	Pairwise Rotation Invariant Co-occurrence Local Binary Pattern	SVM	Swedish	99.38
			Flower102	84.20
Hewitt & Mahmoud (2018)	Shape features & signal features extracted from local area integral invariants (LAIIs)	SVM	Flavia	96.60
			Foliage	93.10
			Folio	91.40
			Swedish	97.80
			LeafSnap	64.90
Zhu et al. (2015)	Shape & color features	SVM	Flower17	91.90
			Flower102	73.10