Real-Time Chinese Chess Piece Character Recognition using Edge AI

This research focuses on developing a character analysis system on Chinese chess pieces (xiangqi) using computer vision technology with the deep learning framework PyTorch. The system is designed to detect and interpret text written on chess pieces in real time, making it easier for players to identify the function of each piece. The implementation is done using a web camera and can be applied to embedded devices such as Jetson Nano. This research aims to develop an automatic recognition system that can help players better understand the game of xiangqi by identifying characters on pieces in real time. The test results show that the system successfully recognized 14 pieces correctly. The system developed using Jetson Nano can directly process image data with a processing time of 0.0222 seconds. This data is obtained from the average of each FPS image from the web camera.