Performance Comparison of Boosting Algorithms in Spices Classification Using Histogram of Oriented Gradient Feature Extraction

Spice classification is an important task in the food industry to ensure safety and quality. This study focuses on of spices using HoG feature extraction method boosting algorithms. The objective this research compare performance four different models algorithms, namely Adaboost Classifier, Gradient Boosting XGB Light GBM classifying spices. evaluation metrics used are Precision, Recall, F1-Score, F2-Score, Jaccard Score, Accuracy. results show that Classifier model achieved best performance, with a precision 0.811, recall 0.809, F1-score while had lowest 0.709, 0.689, 0.682. Overall, indicate fairly good success rate However, further needed improve accuracy results, such as increasing number training data or considering use other methods