• Dr. Devendra Singh

Facial expressions are an essential component of nonverbal communication because they contribute to a more accurate portrayal of the emotions that individuals are experiencing on the inside. There is a direct correlation between a person's feelings and their physical and mental health. There has been a significant increase in the number of people interested in the research of facial expression detection in recent years. Detecting spatial features, managing translation invariance, understanding expressive feature representations, gathering global context, and achieving scalability, adaptability, and interoperability with transfer learning methods are some of the capabilities that the convolutional neural network-10 (DTSA HM RNN AND C DHO HM RNN-10) model possesses. These capabilities make it an appealing candidate for facial expression recognition applications. The model offers a powerful instrument for reliably recognising and comprehending facial expressions, which has applications in a wide variety of domains, such as cognitive computing, human-computer interaction, emotion recognition, and many more. In past research, a number of different deep learning architectures have been suggested as possible solutions to the issue of facial expression recognition. In spite of the fact that many of these studies perform well on image datasets that are collected in a controlled setting, they struggle when confronted with datasets that are more varied and difficult, such as those that include more photographs and partial faces. The DTSA HM RNN AND C DHO HM RNN-10 and the ViT algorithm were used in this research project in order to categorise facial expressions of emotion. Comparisons were made between the recommended models and VGG19 and INCEPTIONV3 in order to assess them. Following the FER-2013 model with an accuracy score of 84.3% and the JAFFE model with a score of 95.4%, the DTSA HM RNN AND C DHO HM RNN-10 model got the best accuracy score of all the models that were tested on the CK+ dataset.

Facial Expressions, DTSA HM RNN, C DHO HM RNN.

"AN ANALYSIS OF THE PERFORMANCE OF DTSA HM RNN AND C DHO HM RNN APPROACHES IN RECOGNITION OF FACIAL EXPRESSIONS FROM REAL-TIME VIDEO", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.d609-d625, March-2024, Available :http://www.jetir.org/papers/JETIR2403377.pdf

"AN ANALYSIS OF THE PERFORMANCE OF DTSA HM RNN AND C DHO HM RNN APPROACHES IN RECOGNITION OF FACIAL EXPRESSIONS FROM REAL-TIME VIDEO", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppd609-d625, March-2024, Available at : http://www.jetir.org/papers/JETIR2403377.pdf