Recognizing Facial Expressions Across Cultures Using Gradient Features
Keywords:FER, multicultural database, neural networks, nonverbal communication, facial expression classification
The goal of this research is to provide a useful technique for better facial emotion recognition, especially across cultural boundaries. Although people communicate both verbally and nonverbally, face expressions are crucial in determining verbal communication. The previous human-computer interface did not take into account thus much nonverbal communication. We need a system that can recognise and comprehend the intentions and feelings expressed by social and cultural cues. In this article, we present a technique for categorising facial photos into six different categories of expressions. Three phases make up the approach; in the first, we used viola Jones to edit off all but the face from the original image and create new ones. Then a HOG histogram was used to extract gradient characteristics. Last but not least, we used SVM to classify picture characteristics and got encouraging results. Comparing the outcomes of the suggested method to other cutting-edge approaches, they are astounding. With regard to combined cross-cultural datasets, it offers accuracy of 99.97%.