Skip to main content

A Gestures based Hand Controlled Virtual Mouse

Project description

Hand-Controlled-AI-Virtual-Mouse 🖱️👆

Version : 1.0.0.1

The mouse is the one of the wonderfull inventions of the Human Computer Interaction(HCI) Technology.

Currently we are using wired or may be wireless mouses,In real time cases some computers may not support for a physical mouse or may some users may be dealth with some hand problems or handicap and cannot use physical mouse, so this Hand controlled AI Virtual Mouse can be used to overcome this problem. Making a user to control the mouse by reducing the computer human interaction.

FUNCTIONALITIES:

-> This was built using the openCV-python and mediapipe for Detecting and processing the image and mediapipe an open source cross-platform developed by google for media processing and ready-to-use ML solutions for computer vision tasks.

-> Our Hand Controlled Virtual mouse can able to move the mouse anywhere on the screen and can able to perform the click operation.

-> Our Index finger can be used to move the mouse over the screen.

-> When Our Index finger and Thumb come close to each other or touch each other then it performs the click operation.

-> And the PyautoGUI for programmatically control the mouse and keyboard.

Now coming to the code part

The Libraries that need to be installed are written in the requirements.txt file
opencv-python - 4.6.0.66
numpy - 1.23.1
matplotlib - 3.5.2
mediapipe - 0.8.10.1
pyautogui - 0.9.53
pillow - 9.2.0

Install the following necessary pip

pip install opencv-python
pip install numpy
pip install matplotlib
pip install mediapipe
pip install PyautoGUI
pip install PIL

The actual working of the mouse is based on the Hand Landmarks which can be viewed and controlled by opencv and mediapipe.

Our hand contains a total of 21 landmarks.

hand_landmarks

Checkout the Demo Below : 👇

At First The mouse pointer movement is very bad and horrible to see so, I have added a **smoothening** factor that makes the mouse pointer move like a feather.

smoothening = 9
clocx = plocx + (index_x - plocx) /smoothening
clocy = plocy + (index_y - plocy) /smoothening
# you can multiply or divide with the smotthening

If any necessary commits are required to increase the elegance of this repo! i'm always open for a PR.

With this signing off..!!,BHARATH GUNTREDDI ..🤞

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

WaveMote-1.0.0.1.tar.gz (4.9 kB view details)

Uploaded Source

File details

Details for the file WaveMote-1.0.0.1.tar.gz.

File metadata

  • Download URL: WaveMote-1.0.0.1.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.5

File hashes

Hashes for WaveMote-1.0.0.1.tar.gz
Algorithm Hash digest
SHA256 1ef6c1f2bc46a6c22c798df7c84976445878f8d7eaeeed2dbd172135667f7730
MD5 ea51caba9d0ae9903d070d7e07073028
BLAKE2b-256 7f58d9a68fcb021a6771da616363c4e35510c48201cd1414be3a8445b618dadd

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page