AI VIRTUAL MOUSE USING OPENCV

Nishant Pant
Nishant Pant
2023
BSc.CSIT
Semester 5
Downloads 2

This project promotes an approach for Human Computer Interaction (HCI) where cursor movement can be controlled using a real-time camera, it is an alternative to the current methods including manual input of buttons or changing the position of physical computer mouse. It helps in better utilizations of the camera and helps in cost reduction as the hardware cost can be reduced. This will also help in making the laptop cameras better quality and proper utilization of the cameras. The virtual mouse program will constantly acquire real-time images where images will be undergone through a series of filtration and conversion. We will first detect the hand landmarks and then track and click based on these points. We will also apply smoothing techniques to make it more usable. This program is more applicable now a day’s due to the pandemic. We can’t afford to touch the computer screen or press the buttons as it can spread the virus thus, this program is a good solution considering the situation. Hand gestures are responsible for performing all the function that a physical computer mouse performs. We propose a gesture-based interface where users interact with a computer using fingertip detection in RGB inputs. Finally, to control the mouse cursor based on a virtual screen, the fingertip location is mapped to RGB images.

Computer Vision
Image Processing
image pre-processing
ensemble
convolutional neural network
sigmoid function
pooling
Feature Extraction
Computer Vision
Image Processing
image pre-processing
ensemble
convolutional neural network
sigmoid function
pooling
Feature Extraction

Similar Projects