Loading repository data…
Iliaromanov / repository
Computer vision based hand gesture controlled mouse pad and volume controller for the Windows OS with speech to text typing functionality
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
Computer vision based alternative to a physical mouse and keyboard built using computer vision with Python, OpenCV and Mediapipe. Allows intuitive hand gesture based control of mouse motion and mouse buttons, a hand gesture based master volume slider for convenience, and speech-to-text typing functionality using google's web speech to text API also triggered by hand gesture.
Note that the GUI window in the top right is used mainly for demonstration purposes and can be minimized without any changes in functionality.
Power Button
To toggle the controller on and off users can hover their index finger over the power button in the top right corner of the capture video. The toggle makes a sound so it can be used even when the capture video window is minimized by just moving the hand in top right corner direction until the sound is played. This feature helps prevent users from unintentionally triggering actions with the controller.
Mouse Pad and Volume Controller
To use the mouse pad or volume controller the users hand must be in the dedicated area outlined in blue on the feedback window. When a hand is detected in a controller area, the area is outlined in green as can be seen in the demo below. There are also sound effects when a hand enters or leaves these areas that are useful when the feedback window is minimized. Both controllers operate based on the location of the index finger.
Left and Right click
To left click bring your middle finger up with your index and move them together. To right click bring out your thumb with your index finger and move them together. For both click types the mouse stops moving at the position where the secondary finger is lifted to make it easier for the user to accurately click. The clicks are activated when the distance between the index and secondary finger is less than a certain threshold and the middle circle turns green when a click occurs.
Note that this version of the left click presses the left mouse key and immediately releases it. Thus, it is useful for double-clicks as demonstrated in the above demo gif when opening the images folder
Selected from shared topics, language and repository description—not editorial ratings.
zaina-ml /
A visual-based graph node editor for training computer vision models.
85/100 healthNadavIs56 /
A Python-based computer vision and AI system for skin disease recognition and diagnosis. Led end-to-end project pipeline, including data gathering, preprocessing, and training models. Utilized Keras, TensorFlow, OpenCV, and other libraries for image processing and CNN models, showcasing expertise in deep learning and machine learning techniques.
72/100 healthHold Down Left Click
To hold down the left mouse key lift your pinky up with your index finger and to release it lower your pinky. The cursor does not stop moving when the left mouse key is pressed this way and will be positioned based on the location of the index finger as it is in default mouse motion mode. This method can be used for single clicks, but is more useful for dragging and dropping items since the mmouse key is not released immediately after it is pressed.
Speech to Text
To trigger speech to text recognition lift your pinky and thumb. This hand position does not need to be held up the entire time you are talking, the voice recording will end when you stop talking and then you may make the gesture to trigger it again. Supported special characters are 'exclamation mark' → !, 'question mark' → ?, 'period' → ., 'comma' → ,, 'space', → ' ', and numeric characters.
More cool new features coming soon!
git clone https://github.com/Iliaromanov/Resume-Chat-Bot.git
cd AI-Based-Desktop-Controller
pip install -r requirements.txt
python mainGUI.py
krishnakumaragrawal /
AI based Online Exam Proctoring System is an innovative project designed to maintain the integrity and security of online exams using Python and Computer Vision.
71/100 healthchs74515 /
In present days, people detection, tracking and counting is an important aspect in the video investigation and subjection demand in Computer Vision Systems. Providing (real time) traffic information will help improve and reduce pedestrian and vehicle traffic, especially when the data collected is learned and analyzed over a period of time, which makes its highly essential to identify people, vehicles and objects in general and also accurately counting the number of people and/or vehicles entering and leaving a particular location in real time. To perform people counting, a robust and efficient system is needed. This research is aimed at making a pedestrian traffic reporting system for certain areas and buildings around the campus to potentially help ease traffic circulation. Providing this information will be done through a developed application, which includes image processing with Open Computer Vision (OpenCV). This will show the amount of traffic in certain buildings or area over a period of time. OpenCV is a cross-platform library which can be used to develop real-time Computer Vision applications [Opencv, 2015b]. It is mainly focused on image processing, video capture and analysis including features like people and object detection. The operations performed were based on the performance and accuracy of the tracking algorithms when implemented in embedded devices such as the Raspberry Pi and the Tinker Board. The Pi Camera was used for real time vision and hosted on the embedded device. The proposed method used was conjoined with an open-source visual tracking implementation from the contribution branch of the OpenCV library and a unique technique for people detection along with different Filtering Algorithms for tracking this. The programming language of choice to implement these features (Tracking and Detection) is python and its libraries. The present work describes a standalone people counting application designed using Python OpenCV and tested on embedded devices ranging from the Raspberry Pi3 to a Tinker Board and a compatible Camera. All these were used in prototyping the design of this application. The results reported and showed that the Person-Counter system developed counted the number of people entering the designated area (down), and the number of people leaving (up).
43/100 healthkaushikjadhav01 /
Computer Vision model creates a live video sketch of frames through real time web cam video. Source code is written in python and model is based on OpenCV. Keras and Numpy have been used to optimize the performance of the model and posterize frames
57/100 healthshukur-alom /
This project utilizes the custom object detection model to monitor parking spaces in a video feed. It identifies vehicles in the video and overlays polygons representing parking spaces on the frames. The program then calculates the number of occupied and free parking spaces based on the detected vehicles and the predefined parking space polygons.
59/100 health