<![CDATA[This research aims to develop a facial expression recognition system based on the JAFFE dataset which includes seven classes of emotional expressions, namely happy, sad, angry, afraid, disgusted and neutral expressions. The first step taken is canny segmentation on each dataset to maintain essential information on each face. Next, extraction was carried out using the hu moments method to gain an in-depth understanding of the important characteristics of facial expressions. The next process involves ensemble voting using five classification methods, namely Naive Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Gaussian Process Classifier (GPC), and Decision Tree. The results of these five methods are then ensembel using voting techniques, and the final results are evaluated using performance metrics such as accuracy, precision, recall, and F-1 score. Evaluation is carried out by comparing the final results with the original data from the JAFFE dataset, by measuring accuracy , precision, recall, and F1 Score value to evaluate system performance. The results of this research show that the ensemble voting approach using a combination of classification methods is able to significantly improve facial expression recognition capabilities. The resulting accuracy, precision, recall, and F1 Score values provide a comprehensive picture of system performance. This research contributes to the development of facial emotion recognition technology and can be applied in various contexts. Includes human-computer interaction as well as applications in the fields of artificial intelligence.Keywords: Performance Analysis, Ensemble, Jaffe Image, Classification, Multiclass]]>
Copyrights © 2024
