Improved Convolution Neural Network for Image Vision Applications

Abstract

Human’s express more through their body language and face than through words. It is natural and most powerful, emotional tool of expression. The recognition of facial expression is a difficult task. Various people show the same expression in a different way. The environment in which the expression is to be detected also adds extra factors, such as brightness, background, pose as well as other objects in the surroundings. Hence, the facial expression recognition is still a challenging problem in computer vision. The solution to this problem can be proposed as facial expression recognition that uses a combination of Convolutional Neural Network and specific image pre-processing steps. It described the innovative solution that provides efficient face expression and deep learning with convolutional neural networks (CNNs) has achieved great success in the classification of various face emotion like happy, angry, sad and neutral. A variety of neuron-wise and layer-wise visualization methods were applied using a CNN, trained with a publicly available from given image dataset. So, it’s observed that neural networks can capture the colors and textures of lesions specific to respective emotion upon diagnosis, which resembles human decision-making.