Automated CNN model for Indian Sign Language Gesture Recognition

This paper presents the development and evaluation of a Convolutional Neural Network (CNN)-based model for the real-time recognition of Indian Sign Language (ISL) gestures. With the objective of enhancing communication for the deaf and hard-of-hearing community, the study navigates through the process of dataset creation, model training, and deployment for real-time sign interpretation. Leveraging a comprehensive dataset sourced from Kaggle, the research focuses on a subset of ISL gestures, employing advanced data preprocessing techniques, model architecture design, and machine learning frameworks facilitated by Google Colab's computing resources. The performance of the developed model is rigorously assessed using a validation set, with results analyzed through a confusion matrix, and metrics such as accuracy, precision, recall, and F1 score. These evaluations underscore the model's efficacy in recognizing ISL gestures with high accuracy, offering promising implications for real-world applications as an assistive technology.