|
| Reference | Features | Dataset | Algorithm | Accuracy (%) |
|
| [55] | Texture and shape features | Medicinal plant specimen library of anhui university of traditional Chinese medicine | SVM classifier | 93.3% |
|
| [56] | Perimeter, a number of vertices, length, width, perimeter and area of hull, colour | Dataset of 24 different plant species having 30 images each from the tropical island of Mauritius | Random forest classifier | 90.1% |
|
| [57] | Leaf shape and venation structure features | Philippine herbal medicine plants using leaf features | Logistic regression, naïve bayes, K-nearest neighbor (KNN), linear discriminant analysis, classification and regression trees, SVM, and neural networks (NN) | 98.6% |
|
| [58] | Texture, colour, and shape | Herbal medicinal plants on a dataset containing 50 different species having 500 leaves. | Neural networks | 93.3% |
|
| [59] | Color, texture and shape feature | Ayurvedic medicinal plant | SVM | 96.66% |
|
| [60] | Centroid contour curve form signature, a fine-scale margin feature histogram and an interior texture feature histogram | Fisher’s iris plant, wheat seed kernels, and 100 plant leaves | Extreme learning machine (ELM) algorithm with K-nearest neighbor, decision tree classifier, support vector machine, naive bayes classifier, and a multilayer perceptron trained with backpropagation algorithm | Iris data set (97%) Seed data set (96%). |
|
| [61] | Shape, texture, and colour | A total of 3,150 leaf photos from 25 different herbal, fruit, and vegetable species | Support vector machine, K-nearest neighbors, multilayer perceptron, random forest, and decision tree algorithms | 85.82 |
|
| [62] | 14 features were selected using a chi-square feature selection strategy | Six varieties of medicinal plant leaves | Multilayer perceptron, random forest, logit-boost, basic logistic, and bagging | 99.01% |
|
| [63] | Morpho-colourimetric parameters Visible (VIS)/Near infrared (NIR) spectral analysis | 20 different Chinese medicinal plants | ANN model | 98.3% |
|
| [64] | Texture and colour features | Swedish leaf dataset | Multiclass-support vector machine | 93.26%. |
|
