Towards Smart Interaction: Hand Gesture Recognition Using Machine Learning in IoT Scenarios

Abstract

Hand gesture recognition is becoming popular in computer vision applications like sign language interpretation, IoT robotic controls, and home automation. In this paper, we propose a gesture recognition system using two machine learning models, VGG16 and MobileNet, and compare their performance in detecting hand gestures. Our dataset consists of over 20,000 images of ten different hand gestures that allow us to implement transfer learning and adapt the pre-trained models by customizing the fully connected layers. Our findings indicate that the MobileNet model outperforms VGG16 model in recognizing hand gestures. The paper focuses on creating a baseline that can combine different models to produce a more efficient result.