Back to Projects
Computer Visionadvanced

Sign Language Detection Systems For Deaf And Mute Individuals

The Sign Language Detection System is an end-to-end deep learning application designed to bridge the communication gap between deaf/mute individuals and the hearing community. The system uses YOLOv5 (You Only Look Once v5) — a state-of-the-art real-time object detection model — to recognize and classify hand gestures representing sign language symbols from images or live camera feeds. The application is served via a Flask web server and is deployed to AWS using a fully automated CI/CD pipeline powered by GitHub Actions and Docker*

10 lectures

What You Will Learn

Master the end-to-end Machine Learning project lifecycle from data collection to cloud deployment.
Implement real-time object detection using the YOLOv5 deep learning model.
Understand how to fine-tune pre-trained YOLOv5 models on custom datasets for sign language gesture detection.
Gain experience building RESTful web applications with Flask for serving ML model predictions.
Develop and deploy Dockerized applications on AWS cloud infrastructure (ECR & EC2).
Build a fully automated CI/CD pipeline using GitHub Actions for continuous integration and deployment.
Learn image preprocessing techniques including Base64 encoding/decoding for web-based inference.

System Architecture

Sign Language Detection Systems For Deaf And Mute Individuals Architecture Diagram

High-level architecture overview of the Sign Language Detection Systems For Deaf And Mute Individuals .

What You'll Build

  • A "Sign Language Detection System" capable of detecting sign language gestures in images and live camera feeds to help bridge the communication gap for deaf and mute individuals.
  • A YOLOv5-powered detection engine fine-tuned on custom sign language datasets with optimized inference parameters.
  • A Flask-based backend API that accepts image uploads, runs YOLOv5 inference, and returns annotated detection results.
  • A user-facing web application with image upload and live webcam detection capabilities using Bootstrap UI.
  • A fully automated CI/CD pipeline that builds Docker images, pushes to AWS ECR, and deploys on AWS EC2.

Project Instructor

Boktiar Ahmed Bappy

Boktiar Ahmed Bappy

5+ years exp
LinkedIn
Sign Language Detection Systems For Deaf And Mute Individuals
Premium
One Subscription. 40+ Projects. Unlimited Access.
AccessMobile & Web