{"id":25943335,"url":"https://github.com/ay-ritesh/sign-language-recognition","last_synced_at":"2026-05-10T03:20:50.516Z","repository":{"id":279032122,"uuid":"937528595","full_name":"Ay-ritesh/Sign-Language-Recognition","owner":"Ay-ritesh","description":"Crafted a deep learning-based system for real-time sign language recognition, leveraging computer vision and neural networks. The system translates hand gestures into text to bridge communication gaps for the hearing-impaired.","archived":false,"fork":false,"pushed_at":"2025-02-23T09:37:22.000Z","size":98066,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-04T07:15:43.412Z","etag":null,"topics":["cnn","keras","nlp","opencv","python","real-time-detection","tenserflow","yolov5"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ay-ritesh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-23T09:29:14.000Z","updated_at":"2025-02-23T09:48:37.000Z","dependencies_parsed_at":"2025-02-23T10:36:36.129Z","dependency_job_id":null,"html_url":"https://github.com/Ay-ritesh/Sign-Language-Recognition","commit_stats":null,"previous_names":["ay-ritesh/sign-language-recognition"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Ay-ritesh/Sign-Language-Recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ay-ritesh%2FSign-Language-Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ay-ritesh%2FSign-Language-Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ay-ritesh%2FSign-Language-Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ay-ritesh%2FSign-Language-Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ay-ritesh","download_url":"https://codeload.github.com/Ay-ritesh/Sign-Language-Recognition/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ay-ritesh%2FSign-Language-Recognition/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262248832,"owners_count":23281838,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cnn","keras","nlp","opencv","python","real-time-detection","tenserflow","yolov5"],"created_at":"2025-03-04T07:15:53.753Z","updated_at":"2026-05-10T03:20:50.509Z","avatar_url":"https://github.com/Ay-ritesh.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🤟 An Enhanced Deep Learning Approach for American Sign Language (ASL) Recognition\n\nA real-time sign language recognition system using **YOLOv5 + CNN + OpenCV**, designed to translate hand gestures into readable text.  \nThe project helps bridge the communication gap between **sign language users and verbal speakers**, promoting inclusivity in healthcare, education, and public services.  \n\n---\n\n## 👨‍🔬 Team Details\n\n| Name | Reg. No. | Contribution |\n|------|----------|--------------|\n| Aayush Amritesh | 21BCE2331 | Data Preprocessing, Model Training \u0026 Testing, Evaluation |\n| Dev Chandrakar | 21BCE2960 | Literature Survey, Dataset Collection, Documentation |\n| Aditya Kumar Jha | 21BCE3759 | Model Selection, UI/Backend Integration |\n\n🧑‍🏫 **Guided by:** *Dr. Viswanathan A., Associate Professor (Sr.)*  \nSchool of Computer Science and Engineering, VIT  \n\n---\n\n## 🎯 Objective\n\nDevelop a **real-time ASL Recognition System** that:\n- Detects gestures using **YOLOv5**\n- Classifies gestures using **CNN**\n- Translates gestures to text through a simple user interface\n- Supports low‐cost consumer hardware like webcams \u0026 laptops  \n\n---\n\n## 🔍 Problem Motivation\n\nOver **70M people** rely on sign language. Most verbal speakers don’t understand it, causing a *communication barrier* in critical areas such as hospitals, classrooms, and public services.  \nDeep learning enables **accessible, affordable, and real-time solutions** for gesture recognition.  \n\n---\n\n## 🏗️ System Architecture\n\n**Modules:**\n1. 📷 *Data Acquisition* – Webcam or image input  \n2. 🧹 *Preprocessing (OpenCV)* – Background removal, segmentation  \n3. 🎯 *Gesture Detection (YOLOv5)* – Identify hand gesture  \n4. 🧠 *Classification (CNN)* – Recognize gesture category  \n5. 💬 *Sign-to-Text Translation* – Output real-time prediction  \n6. 🖥️ *User Interface* – Minimal \u0026 user-friendly  \n\n---\n\n## 🧰 Tools \u0026 Technologies\n\n| Category | Tools |\n|----------|-------|\n| Programming | Python |\n| Deep Learning | YOLOv5, CNN (TensorFlow/PyTorch) |\n| Image Processing | OpenCV |\n| UI/Development | Jupyter/Colab/VS Code |\n| Hardware | Standard webcam, i5/8GB RAM laptop |\n\n---\n\n## 📊 Dataset \u0026 Parameters\n\n| Feature | Value |\n|--------|--------|\n| Image Size | 224×224 |\n| Classes | 6 (Hello, Yes, No, Thanks, Please, I Love You) |\n| Model | YOLOv5s + Custom CNN |\n| Optimizer | Adam |\n| Latency | **\u003c 100ms real-time** |\n\n---\n\n## 🚀 Result Summary\n\n✔ **Real-time gesture detection**  \n✔ Works effectively in **low-light \u0026 diverse backgrounds**  \n✔ Runs smoothly on **consumer-grade hardware**  \n✔ Achieved **95% accuracy (static)** \u0026 **90% dynamic** in adequate lighting conditions \n\n---\n\n## 🏁 Conclusion\n\nThe system successfully bridges the communication gap by converting American Sign Language (ASL) gestures to readable text in real time using a hybrid deep learning model (YOLOv5 + CNN). It is affordable, portable, and scalable, making it suitable for deployment in schools, hospitals, and public service centers. Future work includes sentence-level recognition, multi-language support, and mobile deployment.\n\n---\n\n## 🔮 Future Enhancements\n\n- 📌 Support for complete sentence-level gesture recognition  \n- 🌎 Extension to multiple sign languages (e.g., ISL, BSL, etc.)  \n- 📱 Mobile application deployment on Android/iOS  \n- 🎙️ Voice output for recognized text (sign-to-speech)  \n- 🧠 Use of Transformer-based or sequence models for better temporal gesture understanding\n\n---\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fay-ritesh%2Fsign-language-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fay-ritesh%2Fsign-language-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fay-ritesh%2Fsign-language-recognition/lists"}