A set of pictures have been recorded from a webcam containing different angles of a thumbs up.
Images have been labelled using bounding boxes.
Yolov5 model has been trained on the said set of images and managed to achieve an average accuracy of 75% on the test data.
The accuracy of the model can be greatly increased by increasing the number of training data and bringing more variaty to allow better generalization of the class(Thumbs Up).
Next steps in this project would be to increase the number of hand gestures (classes) as well as the number of training data to get a more functional and accurate model.