• Poonam Gujre
• Sudha Sharma
• Trapti Sharma
• Durgesh Mishra

Face expression recognition is essential in a wide variety of applications. The traditional feature extraction technique is used to complete a task of this kind, which needs a large amount of handling. Beforehand, several deep neural networks were utilized aimed at this purpose; however, several newer and probably superior techniques may now be used. Consequently, the purpose of this research is to provide a strategy for detecting faces that integrates the convolutional neural network (CNN) and image edge identification. The suggested method is divided into two stages: the first includes standardizing the facial expression in the image, and the second leverages convolution for image edge extraction. The procedure known as maximum pooling is then utilized to reduce the dimensionality. The expression is recognized once the Softmax classifier has completed categorizing it. The Fer-2013 dataset was used to complete the facial expression recognition study. The proposed technique can achieve an expression recognition rate of up to 99.68 percent aimed at the dataset being used. The presented approach takes fewer iterations to achieve recognition, and the system runs 5 to 15 times quicker than the SDSRN, AlexNet, and VGGnet algorithms.

CNN ,AlexNet,VGGnet, Softmax classifier.

"Facial Expression Recognition using Deep Learning Algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 2, page no.e184-e189, February-2023, Available :http://www.jetir.org/papers/JETIR2302420.pdf

"Facial Expression Recognition using Deep Learning Algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 2, page no. ppe184-e189, February-2023, Available at : http://www.jetir.org/papers/JETIR2302420.pdf