Hand Gesture Recognition Using CNNs: A Comprehensive Survey

Abstract

Hand gesture recognition has garnered significant attention due to its applications in diverse fields such as human-computer interaction, sign language translation, and virtual reality. This review paper presents a comprehensive survey of the advancements in hand gesture recognition using Convolutional Neural Networks (CNNs). The utilization of CNNs, a class of deep learning algorithms, has revolutionized the accuracy and robustness of gesture recognition systems by enabling the extraction of intricate spatial features from image data. The paper delves into the key approaches and architectures employed for CNN-based hand gesture recognition, highlighting the evolution of model designs and their efficacy in capturing gesture intricacies. The review encompasses an analysis of various datasets, preprocessing techniques, and training strategies utilized for training CNN models. It examines the performance metrics commonly employed for evaluating these models, including accuracy, precision, recall, and F1-score. Real-world applications, ranging from immersive gaming experiences to assistive technologies for differently-abled individuals, are explored, underscoring the practical implications of CNN-driven advancements in the field. Moreover, this survey critically discusses the challenges faced by CNN-based gesture recognition systems, such as dealing with varying lighting conditions, hand poses, and gesture complexities. The paper offers insights into future directions, including multi-modal fusion and enhanced real-time performance, to further improve the accuracy and applicability of hand gesture recognition using CNNs.