Texture features using machine learning techniques for offline facial expression recognition

Abstract

The graduation thesis aims to study and develop a facial expression recognition system using machine learning. Machine learning techniques are utilized to develop models and algorithms for data analysis, pattern recognition, and automatic prediction, without the need for direct programming. In the context of facial recognition and expression analysis, machine learning can be used to develop models capable of classifying different facial expressions. These models are trained on a large dataset containing pre-labeled facial expressions. After training on this data, the model becomes capable of recognizing facial patterns and classifying new expressions presented to it. Several experimental results have been shared in the thesis, using various classification algorithms such as SVM and KNN on the FER2013 dataset. The results have demonstrated satisfactory performance using these algorithms. To improve these results, a set of filters has been applied to the dataset, and the available data volume has been increased. Multiple studies have been conducted on these processes, and better results have been achieved after implementing the enhancements. In general, it can be concluded that the use of SVM and KNN algorithms in facial expression recognition has shown satisfactory results. Additional processes such as filter application and data augmentation have improved performance. This approach holds promise in developing an effective facial expression recognition system using machine learning. These results and proposed enhancements have been comprehensively discussed in the thesis. The research in the thesis aims to expand knowledge and gain a better understanding of machine learning applications in facial expression recognition. It seeks to achieve further advancements and improvements in performance and accuracy. This approach is promising and may contribute to the development of more efficient facial expression recognition systems applicable in various fields.