Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Unified learning approach for egocentric hand gesture recognition and fingertip detection.
| Date | Stars |
|---|---|
| 2026-07-24 | 315 |
| 2026-07-25 | 315 |
| 2026-07-28 | 315 |
| 2026-07-30 | 315 |
| 2026-08-06 | 315 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
## Unified Gesture Recognition and Fingertip Detection 👋 [](https://github.com/MahmudulAlam/Unified-Gesture-and-Fingertip-Detection/stargazers) [](https://github.com/MahmudulAlam/Unified-Gesture-and-Fingertip-Detection/network) [](https://github.com/MahmudulAlam/Unified-Gesture-and-Fingertip-Detection/issues) [](https://github.com/MahmudulAlam/Fingertip-Mixed-Reality) [](https://github.com/MahmudulAlam/Unified-Gesture-and-Fingertip-Detection/blob/master/LICENSE) <img src="https://user-images.githubusercontent.com/37298971/123714340-f8d70800-d82a-11eb-9742-042a5d9334a1.png" width="28"> <p align="justify"> A unified convolutional neural network (CNN) algorithm for both hand gesture recognition and fingertip detection at the same time. The proposed algorithm uses a single network to predict both finger class probabilities for classification and fingertips positional output for regression in one single evaluation. From the finger class probabilities, the gesture is recognized, and using both of the information fingertips are localized. Instead of directly regressing the fingertips position from the fully connected (FC) layer of the CNN, we regress an ensemble of fingertips position from a fully convolutional network (FCN) and subsequently take ensemble average to regress the final fingertips positional output. </p> ## Update 🔥 Included ```robust real-time hand detection using yolo``` for better smooth performance in the first stage of the detection system and most of the code has been cleaned and restructured for ease of use. To get the previous versions, please visit the release [section](https://github.com/MahmudulAlam/Unified-Gesture-and-Fingertip-Detection/releases). <p align="center"> <img src="https://user-images.githubusercontent.com/37298971/77615813-6de9cc80-6f5a-11ea-9172-a95e5604147c.gif" width="400"> </p> <p align="center"> <img src="https://user-images.githubusercontent.com/37298971/72676259-5f45eb80-3ab9-11ea-96d7-436f160a4b84.png" width="600"> </p> ## Requirements 🐍 - TensorFlow-GPU==2.2.0 ```pip install tensorflow-gpu==2.2.0``` - OpenCV==4.2.0 ```pip install opencv-python==4.2.0``` - ImgAug==0.2.6 ```pip install imgaug==0.2.6``` - Weights: [```Download the pre-trained weights```](https://mega.nz/#F!6stCxY5b!oB-3279KkhfhRULQFQO7yQ) files of the unified gesture recognition and fingertip detection model and put the ```weights/``` folder in the working directory. [](https://mega.nz/#F!6stCxY5b!oB-3279KkhfhRULQFQO7yQ) [](https://www.dropbox.com/sh/7pbfrgaor678eft/AAA8r5ADlMde0WkAtJQO_lo5a?dl=0) The ```weights/``` folder contains three weights files. The ```fingertip.h5``` is for unified gesture recognition and fingertip detection. ```yolo.h5``` and ```solo.h5``` are for the yolo and solo method of hand detection. [(what is solo?)](https://github.com/MahmudulAlam/Unified-Gesture-and-Fingertip-Detection/tree/master/hand_detector/solo) ## Paper 📚 [](https://doi.org/10.1016/j.patcog.2021.108200) [](https://arxiv.org/abs/2101.02047) <img src="https://user-images.githubusercontent.com/37298971/141495879-3b3d4ba7-955a-4c1c-bf55-24af31
Excerpt of 7,658 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3a722ef6a6559675, topic:yolo