American Sign Language Alphabet Recognition

Built a computer vision system that recognizes the 26 letters of the American Sign Language alphabet from real-time webcam input. The system captures the user’s hand gestures through a camera and uses a deep learning model to classify the letter being shown.

Due to the lack of a suitable dataset for my specific implementation, I created the dataset manually from scratch. This required learning the ASL alphabet, recording myself performing each letter, and organizing the collected video samples into a structured dataset for training and testing.

The model was built using a multi-layer neural network and trained to recognize gesture patterns from visual input. This project gave me practical experience with the full machine learning workflow, including dataset creation, preprocessing, model training and real-time computer vision integration.