Analyzing human facial expressions using machine vision systems is indeed a challenging yet fascinating problem in the field of computer vision and artificial intelligence. Facial expressions are a primary means through which humans convey emotions, making their automated recognition valuable for various applications including man-computer interaction, affective computing, and psychological research. Pre-processing techniques are applied to every image with the aim of standardizing the images. Frequently used techniques include scaling, blurring, rotating, altering the contour of the image and changing the color to grayscale and normalization. Followed by feature extraction and then the traditional classifiers are applied to infer facial expressions. Increasing the performance of the system is difficult in the typical machine learning approach because feature extraction and classification phases are separate. But in Deep neural networks (DNN), the two phases are combined into a single phase. Therefore, the CNN models give better accuracy in Facial Expression Recognition than the traditional classifiers. But still the performance of CNN is hampered by noisy and deviated images in the dataset. This work utilized the preprocessing methods such as resizing, grayscale conversion and normalization. Also, this research work is motivated by these drawbacks to study the use of image pre-processing techniques to enhance the performance of deep learning methods to implement facial expression recognition. Also, this research aims to recognize emotions using deep learning and show the influences of data pre-processing for further processing of images. The accuracy of each pre-processing methods are compared, then combination between them are analyzed and the appropriate preprocessing techniques are identified and implemented to see the variability of accuracies in predicting facial expressions.

KEYWORDS: Facial Expression Recognition, CNN, Deep neural networks, preprocessing techniques, Normalization, scaling, grayscale.

Dr. T. Velmurugan is working as an Associate Professor in the PG and Research Department of Computer Science and Applications, Dwaraka Doss Goverdhan Doss Vaishnav College, Chennai-600106, India. He holds a Ph.D. degree in Computer Science from the University of Madras. He has 30 years of teaching experience. He guided more than 300 M.Phil., Research Scholars. Also, he guided 23 Ph.D. scholars and currently guiding 6 Ph.D. scholars. He has published more than 175 articles in SCOPUS and SCI indexed journals. He elected and served as a Senate Member from Academic Council, University of Madras. He has a lot of administrative experiences. He served as advisory board member to many academic institutions in and around Tamil Nadu, India. He was an invited speaker and keynote speaker for many international conferences around the world. He served as a nominated Senate Member in the Middle East University, Dubai, UAE for a period of three years. He is a member in Board of studies for many autonomous institutions and Universities. Also, he organized international Conferences and workshops. In addition, he was a resource person for various national workshops entitled "Scientific Research Article Writing and Journal Publications" and many of the recent topics in Computer Science. He is an Editorial Board Member of 10 International Journals. He also a reviewer in many peer reviewed journals like Elsevier, Springer, IEEE and IOSPress Journals etc. He is the Chair person for the Government of Tamil Nadu State for XII standard book titled as “Electronics and Hardwares”. Further, he is a visiting faculty for M.Phil. Course for various universities throughout India. His H index is 21 and i10 index is 31. His area of specialization includes Data Mining, Artificial Intelligence, Machine Learning, Network Security, Big Data Analytics, Data Science and etc.