AIR CANVAS USING AI

Abstract

People are using electronic devices like screens, where we can write, draw and represent various structures, symbols, arts, painting, etc. Either by using mouse or by typing. The project takes advantage of this gap and introduces a new system called the air canvas which focuses on developing a motion-to-text converter that can potentially serve as software for intelligent wearable devices which enables users to draw in mid- air using their hands. The system incorporates object detection techniques in OpenCV to track the hand position and allow real-time drawing. It will be a powerful means of communication for the deaf. All you have to do is think what you want to express or show, and then just move your finger accordingly. The existing project which allows us to draw using a stylus or pen this technology or methodology which takes a lot of process and time. Avoiding or decreasing these limitations we came up with this project that uses new technologies and easy methodologies like Mediapipe which is used to detect the hand gestures under the category of Computer Vision. We are using Python since it is easy to make use of the syntax and understanding the basics as well as it can be implemented in any OpenCV supported languages, NumPy to handle data related to strokes, shapes, or any other canvas elements and it can provide a convenient way to represent and manipulate image processing. Deque stores the strokes and make it visible in the canvas, Mask Window to mask the background and show the text. System Camera is used to track the hand and create drawings just by moving their fingers on the air in front of the camera in a certain distance according to what the user wants to express and this works by monitoring to determine the landmarks of hand, then the finger tips are taken for modes like selection, drawing and clearing the canvas. KEYWORDS: - Canvas, OpenCV, Python, Computer Vision, NumPy, Deque, Mask Window.