In this paper, the authors propose a facial expression recognition system that utilizes RST (Rostrum, Supperior, and Thin) invariant features and texture features to classify six different facial expressions. The system was trained on a dataset of three individuals with a total of 90 border mask samples for training and 30% of the border mask samples for testing. The authors used k-Nearest Neighbor (k-NN) algorithm to classify the expressions and achieved an accuracy of 90% at k=2. The results showed that the Surprise expression had the highest accuracy among all the other expressions. To evaluate the performance of the system, confusion tables were conducted which showed different classification results for each facial expression. The authors concluded that RST invariant features and texture features are effective in recognizing facial expressions and can be used in various applications such as human-computer interaction, emotion recognition, and virtual communication. The paper references 15 sources, providing a comprehensive overview of the state-of-the-art techniques in facial expression recognition and their applications. Overall, the paper provides a practical approach to facial expression recognition using RST invariant features and texture features that can be used in various applications with accurate classification results.

In this paper, the authors propose a facial expression recognition system that utilizes RST (Rostrum, Supperior, and Thin) invariant features and texture features to classify six different facial expressions. The system was trained on a dataset of three individuals with a total of 90 border mask samples for training and 30% of the border mask samples for testing. The authors used k-Nearest Neighbor (k-NN) algorithm to classify the expressions and achieved an accuracy of 90% at k=2. The results showed that the Surprise expression had the highest accuracy among all the other expressions. To evaluate the performance of the system, confusion tables were conducted which showed different classification results for each facial expression. The authors concluded that RST invariant features and texture features are effective in recognizing facial expressions and can be used in various applications such as human-computer interaction, emotion recognition, and virtual communication. The paper references 15 sources, providing a comprehensive overview of the state-of-the-art techniques in facial expression recognition and their applications. Overall, the paper provides a practical approach to facial expression recognition using RST invariant features and texture features that can be used in various applications with accurate classification results.