Video Player Using Action Recognition and Convolutional Neural Networks

Abstract

The whole world, is embracing advanced technology in all areas of life. This is made possible by the interaction between human and Computers (i.e., Human Computer Interaction). In this paper, we are discussing a very innovative way in which this technology of human computer interaction is used to play and control videos. The programmed acknowledgment of human motions from camera pictures is an extremely intriguing point. This technology is now becoming more and more practical as it is being inbuilt into many commercial products. However, here we are dealing with a very different approach in which Convolutional Neural Network (CNN)is used to develop a gesture-controlled video player. The human gestures would be used to control actions likeplay, pause, volume up and volume down. Deep learning techniques can be used to solve the problems that arise in ‘computer vision’ whereas, the parallel nature of CNN, is used to deal with extraction of data sets from images control videos. Convolutional Neural Networks (CNNs) are a type of deep model that can act directly on the raw inputs and they play an important role in the field of Image Recognition and Classification.