Skip to main content

HandGestureRec

Short Summary:

The library is an open source dynamic hand gesture recognition built using python with a Tkinter GUI and ML. using Tensorflow, Keras Api for TF, OpneCV for camera access and MediaPipe for hand landmarks detection https://github.com/AhmadBodayr/HandGestureRec

Implementation:

The library uses the webcam as the sensor and it gives the user access to the webcam using opencv, then the handlandmarks are collected using MediaPipe.

GUI:

The GUI is the main way for the user to interact with the toolkit. It is written in Tkinter for python wich is the default GUI library for Python. The GUI is simple and easy to use.

The Backend:

It is comprised of:

Data Collection:

The data collection is done using OpenCV and MediaPipe, each gesture is composed of 80 videos each is 30 frames, with each frame containing the 42 landmarks for each hand. Each landmark is an X, Y, Z tupple which describes the location of that specific landmark.

Data Storage Strategy:

No DBMS was used instead a folder tree which is composed of 3 submodules was built. The first submodule is a gestures folder that contains all the gestures defined by the user, the second is a datasets submodule which contains all the datasets created by the user. A single dataset is a non null subset of the gestures.

The machine learning algorithm:

The ML. model used is an LSTM model which was built using Tensorflow 2.X and the Keras ApI. for tensorFlow.

How to use:

install the library from $ pip using pip install HandGestureRec and in your python project write in the terminal 'execHandGestureRec'

    1. The user define one or more gesture using the GUI. One gesture is to be defined at a time. The gesture is defined by giving it a name and pressing create gesture then OpenCV will give the user access to the webcam, 80 videos will be taken each is 30 frames in length so the user needs to do the gesture for 80 times. The starting time of each try of the 80 will be shown on the screen.
    1. After the user defines 1 or more gestures, he can then use the datasets submodule to create a dataset which will then serve as an input to the ML. model. To create a dataset the user have to give it a name and choose a subset of the gestures he defiend before hand then press create dataset.
    1. After having one or more datasets the user can then can to the models submodule to crerate a model to a specific dataset. There is a 1:1 relation between the datasets and the models meaning that every dataset can only contribute to only one model.
    1. After creating one or more models the user can test his models using the testing submodule.

Metadata

Release files for HandGestureRec 0.1.7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for HandGestureRec 0.1.7
File Size Uploaded Provenance Actions
HandGestureRec-0.1.7.tar.gz 9.8 kB Without provenance Details for HandGestureRec-0.1.7.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for HandGestureRec 0.1.7
File Interpreter ABI Platform Actions
HandGestureRec-0.1.7-py3-none-any.whl Python 3 none any Details for HandGestureRec-0.1.7-py3-none-any.whl

Total release size: 22.5 kB

Release files / HandGestureRec-0.1.7.tar.gz

Download URL HandGestureRec-0.1.7.tar.gz
Size 9.8 kB
Tags Source
SHA-256 checksum
How to use checksums
c217977ba29bb9676b2f09ad6df56de6998f7ad305266c32d1495d92304156c7
BLAKE2b-256 checksum
How to use checksums
506f70c8cad29546241d4d1fd90fa8ce7aa6658c5bc233fd4cd6f7ff3d9290d3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.10

Release files / HandGestureRec-0.1.7-py3-none-any.whl

Download URL HandGestureRec-0.1.7-py3-none-any.whl
Size 12.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3873bf1e50f36a377c1b86669215e3fd988328b2202f8bd7703536058772757a
BLAKE2b-256 checksum
How to use checksums
1ee718e4d4672d2ed2cdc6cac6ece6533b38b05e349208637c5274425b941b66
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.10

Security for HandGestureRec 0.1.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page