Interactive ASL Alphabet Recognition System for Inclusive Digital Communication

American Sign Language (ASL) is a vital communication medium for the Deaf and Hard-of-Hearing (DHH) community, yet its integration into digital platforms remains limited. This paper presents the development of a real-time ASL alphabet recognition system for virtual text input, designed to detect static ASL hand gestures and convert them into corresponding alphabetic characters. The system employs computer vision techniques using MediaPipe for hand landmark detection and a Random Forest classifier trained on custom gesture data. Two operational modes are implemented: Practice Mode provides immediate visual feedback to help users learn and refine ASL gestures. Keyboard Mode allows users to construct words and sentences using gesture-based input. Built with Python and integrated through a Tkinter-based graphical user interface, the application runs efficiently on standard webcams without requiring specialized hardware. The system is designed to be user-friendly and educational, making it accessible to ASL learners and regular users seeking alternative input methods. The project demonstrates a lightweight, accessible solution to support ASL education and communication, highlighting the potential of AI-powered assistive technologies in promoting inclusivity and accessibility in human-computer interaction.