Abstract:
TOUCHLESS TOKEN GENERATION SYSTEM is a software solution that generates
tokens without physical contact or manual interaction. It helps in reducing wait times,
increasing customer satisfaction, and reducing the interaction between people or objects. In
the current scenario, it is equally important to have an automated system and avoid the spread
of diseases through unsanitary touch. The proposed system can be used to overcome the
existing manual token dispenser by employing a webcam or a built-in camera for capturing
hand gestures and hand tip detection using computer vision to generate tokens. The system
makes use of machine learning classification algorithms such as RandomForest, DecisionTree,
NaiveBayes, SVM, and KNN to train the model. The SVM classifier achieved an accuracy
rate of 98.47%, which was the highest among all the classifiers. Based on hand gestures, the
computer can be controlled virtually and can perform token generation without the use of a
physical object. The system uses computer vision library to fetch input frames from the video
capturing the hands. It uses Mediapipe framework to detect hand gestures thereby marking
significant landmarks. Each time a hand gesture is detected the token count increases. Hence,
the proposed system eliminates the need for physical contact reducing the risk of spreading
infection and contamination. Tokens can be generated quickly and easily making the process
faster and more convenient for users
