Performance of CNN for different facial expression images with varying input dataset sizes

Image classification is one of the computer vision problems. It is a supervised learning technique, in this, images are classified according to their different characteristics (features). There are various facial image datasets of different persons with different facial expressions. Classification based on different facial expressions is always a challenging task for researchers because a person can have different facial expressions like smiling, sad, normal, with or without goggles, etc., depending upon the mood of the person. Deep learning technique like Convolutional neural networks (CNN) is an indemand technique to classify images based on their features. This paper demonstrates the performance of CNN using a different number of images with different numbers of expressions per person and keeping all the other parameters the same. For performance measurement of CNN, the faces94 dataset of is used. Based on the evaluated results, some important points are highlighted.