Sign Language Recognition SLR is a method used to identify and interpret the sign language gestures or movements. The inability to speak among the deaf-muted community is a significant communication challenge. To bridge this gap, Sign language recognition enables effective communication for the deaf-muted community while assisting others to familiarize themselves with sign language actions. The focal point of this research was to build a model utilizing Computer Vision and Deep Learning to recognize and forecast static signs of hand gestures corresponding to their respective English alphabets. Specifically, it addresses the problem by optimizing the model’s accuracy compared to existing models and previously tested works by other researchers, aiming to effectively recognize static hand gestures of the English alphabet. A specialized dataset from MNIST was chosen, which contains static snapshots of hand motions representing the English alphabets. The suggested model used a CNN Architecture with 10 layers and achieved an accuracy of 96.95% in training and 95.23% in testing. The model is intended to serve as a foundation for future investigation in sign language recognition, wherein people can be provided an accessible tool, to learn the basics of sign language accurately. The future scope of this project could explore extending this model’s functionalities to actually being able to recognize full words and possibly build a real-time model.