In the context of this study, convolutional neural networks (CNNs) have been developed with the objective of identifying facial expressions. The primary aim of this study project is to categorize each facial image into one of the seven distinct categories of facial expressions under investigation. The training of Convolutional Neural Network (CNN) models with different levels of depth included the use of grayscale photographs sourced from the Kaggle website [1]. By using Torch [2], we successfully developed our models and used the computational capabilities of Graphics Processing Units (GPUs) to enhance the efficiency of the training procedure. In addition, we used a hybrid feature method alongside the networks that were operating on raw pixel data. By integrating raw pixel data with Histogram of Oriented Gradients (HOG) characteristics, we were able to train a distinctive CNN model [3]. We used several techniques, including dropout and batch normalization, along with L2 regularization, to mitigate the occurrence of overfitting in the models. Cross-validation was used to determine the optimal hyper-parameters, and the performance of the generated models was assessed by examining their individual training histories. Furthermore, we provide a visual representation of the several layers inside a network to illustrate the attributes of a facial feature that may be acquired using Convolutional Neural Network (CNN) models.
Face Recognition, Image Processing, Computer Vision, Emotion Detection, OpenCV
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.