Deep Learning based Lip Movement Technique for Mute

There is a significant change in technology, virtual reality (VR) has been used in this article as the simplest way of visual activity and interaction technique which provides visual nodal options supported by the automated lip-reading technology. With this advancement in the technology, the state of the human can be identified and captured through the lip movements. Deep Learning is used to analyze the real time thinking of the human visual choices. Using image processing technique, virtual reality technology is used to identify the driver's visual features and evaluate the critical time thinking. The ancient lip-reading recognition system, the need for responsive applications is difficult to fulfill. Deep Learning is now the emerging technique of artificial intelligence which acts as a normal human brain with the thinking capability. It consists of different layers which are used to evaluate the details like neurons in brain. In this article, the surface area of the lip is taken as the key element or the key feature of the lip movement. The horizontal distance and the vertical distance of the lips are used to calculate the surface area. This surface area is then used to estimate some parameter and store in the database. Based on the results, the accuracy is more than 85%. Therefore, our proposed system is more effective and more efficient than other traditional methods.