Custom Hand Gesture Recognition with Hand Landmarks Using Google’s Mediapipe + OpenCV in Python

Hey what's up, y'all! In this video we'll take a look at a really cool GitHub repo that I found that allows us to easily train a Keras neural network to recognize our own custom hand gestures, and that runs flawlessly on a CPU. But there's more: I'll actually guide you through the entire process and explain the logic of how everything works behind the scenes too. We'll use Mediapipe for extracting hand landmarks (which runs a pipeline of TensorFlow neural nets under the hood), which will allow us to use relatively small training datasets for training on our new custom hand gestures. GitHub repository (translated into English): https://github.com/kinivi/hand-gestur... Original GitHub repository (in Japanese) https://github.com/Kazuhito00/hand-ge... A series of videos I made about OpenCV:    • Learn OpenCV by MAKING MEMES   Here's the same repo but in React, and nextJS: https://github.com/TomasGonzalez/hand... Follow me on GitHub: https://github.com/ivangrov Hit me up on Twitter:   / ivangrov   ( Cool updates on more videos I'm making there) And on LinkedIn:   / ivangrov   Time stamps⏳ 00:00 Intro 01:14 What's gonna be in the video 04:00 Top-level overview of the hand gesture recognition approach we'll use 14:56 Google's Mediapipe framework Python API 17:50 Hand gesture recognition GitHub repository we'll use 20:58 Modifying the repo's code to allow for multi-hand detection 25:23 Code walkthrough 32:46 Explaining hand landmarks preprocessing algorithm 48:05 Disabling point history classification 50:43 Training: hand gesture dataset 53:30 Training: adding a new hand gesture to the existing ones 01:02:43 Training: Retraining the model with all new hand gestures 01:09:51 Outro Contact me directly: [email protected] ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ It would mean the world to me, if you decided to support me and the channel =) ►You may consider watching ads that show up on the videos Making these videos takes a lot of time and effort, so If you decide to support me, please don't hesitate get in touch with me as I'd like to thank you personally! ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ Thanks for watching!