Convolutional Neural Network-Based Recognition of Human Hand Gestures for Smart Elevator Control

The proposed paper presents a hand gesture recognition-based elevator control system using a convolutional neural network model which provides an efficient and convenient way to control elevators by recognizing hand gestures and issuing commands to the elevator control unit. The system captures an image of the user's hand motions via a camera, which are subsequently processed by the CNN model. To correctly identify the various hand gestures, the model is trained on a dataset of hand gesture images using Python and TensorFlow. Once the gesture is recognized, the system sends a command to the elevator control unit to move the elevator to the desired floor. The proposed system has several advantages over traditional elevator controls, such as improved accessibility, reduced physical contact, and improved user experience. The system is especially useful for people with disabilities who may have difficulty using conventional elevator controls. The paper discusses the design and implementation of the CNN model and its integration with the elevator control system. By placing the system to the test on a collection of hand gesture images and comparing the results with traditional elevator control methods, the system's performance is assessed. The studies showed that the suggested approach is more efficient than conventional elevator control systems and has a high detection performance. Overall, the paper demonstrates the feasibility of using hand gesture recognition as an alternative to traditional elevator controls. The proposed system has the potential to revolutionize the way elevators are controlled, making them more efficient and user-friendly. The paper concludes by discussing future directions for research in this area, including the development of more sophisticated CNN models and the integration of the system with other smart building technologies.