Rock-Paper-Scissors Image Classification Using Transfer Learning

Games are a genre of deliberate mental or physical activities which can be done alone or in groups for the purpose of enjoyment and recreation. Every game has its unique collection of participants, movements, and tactics, in addition to its own set of principles and guidelines. Rock-Paper-Scissors is probably the most well-known game for determining a winner in the world. The rules are pretty straightforward. Rock, paper, or scissors are displayed by each player simultaneously. The rock defeats the scissors but is defeated by the paper. Scissors defeat paper but lose to rock and paper defeats rock but loses to scissors. Using hand images, this study proposed identifying images of hands playing rock-paper-scissors. Transfer learning is used in the proposed model to recognize and classify images of rock-paper-scissors. The dataset for this study was acquired from the Kaggle. There are 2188 images in the dataset, including 712 rock images, 726 paper images, and 750 scissor images. The dataset is divided into two parts: 80% is utilized for training the model, and 20% is utilized for model validation. The RPSICTL model evaluation results good validation accuracy of 99.54%.