Textural Analysis for Medicinal Plants Identification Using Log Gabor Filters

Texture plays a crucial role in computer vision, providing valuable information about image regions. Log Gabor filters that mimic the human eye’s visual cortex are used as feature extractors to identify medicinal plants based on leaf textural features. This method was tested dataset developed from Centre of Plant Medicine Research, Ghana, consisting forty-nine (49) plant species well Flavia and Swedish Leaf datasets, which benchmark datasets. The filter outperformed filters, have been extensively this area when nine supervised classifiers (K-Nearest Neighbour, Support Vector Machine, Naïve Bayes, Logistic Regression, Decision tree, Random Forest, Multilayer Perceptron, Gradient Boosting Stochastic Descent) with 10-fold cross-validation. Machine Perceptron were best performing for both terms accuracy, precision, true positive rate, F1 score false rate. filter’s highest accuracy 79% Mydatastet, 97% Flavia, 98% whiles 66% 92% 96% dataset.