{"id":21538290,"url":"https://github.com/ankitjha2202/object_detection_services","last_synced_at":"2026-05-19T00:34:47.250Z","repository":{"id":263315127,"uuid":"889043829","full_name":"Ankitjha2202/object_detection_services","owner":"Ankitjha2202","description":"License plate detection using yolov8 oriented bounding boxes","archived":false,"fork":false,"pushed_at":"2024-11-18T04:41:19.000Z","size":74136,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-16T09:29:38.846Z","etag":null,"topics":["computer-vision","flask","rest-api","yolov8","yolov8-detection"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ankitjha2202.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"license-plate-detection.ipynb","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":"2024-11-15T13:57:26.000Z","updated_at":"2024-11-18T04:41:22.000Z","dependencies_parsed_at":"2024-11-17T20:36:22.956Z","dependency_job_id":null,"html_url":"https://github.com/Ankitjha2202/object_detection_services","commit_stats":null,"previous_names":["ankitjha2202/object_detection_services"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Ankitjha2202/object_detection_services","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ankitjha2202%2Fobject_detection_services","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ankitjha2202%2Fobject_detection_services/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ankitjha2202%2Fobject_detection_services/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ankitjha2202%2Fobject_detection_services/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ankitjha2202","download_url":"https://codeload.github.com/Ankitjha2202/object_detection_services/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ankitjha2202%2Fobject_detection_services/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33196185,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-18T09:27:30.708Z","status":"ssl_error","status_checked_at":"2026-05-18T09:27:28.300Z","response_time":71,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["computer-vision","flask","rest-api","yolov8","yolov8-detection"],"created_at":"2024-11-24T04:11:35.201Z","updated_at":"2026-05-19T00:34:47.236Z","avatar_url":"https://github.com/Ankitjha2202.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Object Detection Using YOLOv8  \n\nThis project delivers a **comprehensive solution** for **license plate detection** using the state-of-the-art YOLOv8 object detection model. From dataset preparation and model training to developing a robust Flask API, this repository is your one-stop guide to implementing real-time license plate detection.  \n\n---\n\n## 🚀 **Project Highlights**  \n\n- **Oriented Bounding Boxes (OBB):** Handles rotated license plates with precision.  \n- **Flask API Integration:** Provides an easy-to-use web interface for detection.  \n- **GPU-Accelerated Training:** Powered by Kaggle for efficient model training.  \n- **Visualization-Ready:** Clear and insightful results showcased in a Jupyter Notebook.  \n\n---\n\n## 🛠️ **Features**  \n\n### 1️⃣ **Dataset Preparation**  \n- Dataset sourced from **Roboflow** with high-quality annotations.  \n- Preprocessing steps include scaling, augmentations, and proper formatting for YOLOv8.\n\n### 2️⃣ **YOLOv8 Training**  \n- Trained on a Kaggle **GPU environment** for optimal performance.  \n- Model trained for **10 epochs** (for better prediction we can train for more epochs).\n- The best model weights (`best.pt`) are ready for deployment.  \n\n### 3️⃣ **Flask API**  \n- **User-Friendly Interface:** Upload images via the web interface for detection.  \n- **AI-Powered Backend:** Returns:  \n  - Images with annotated bounding boxes.  \n  - JSON files with bounding box coordinates and class labels.  \n\n### 4️⃣ **Inference and Visualization**  \n- Intuitive visualization of results through bounding boxes and JSON outputs.  \n- Detection results include bounding box **coordinates**, **angles**, and class **labels**.  \n\n---\n\n## 📊 **Example Results**  \n\nSee the YOLOv8 model in action below:  \n\n**Example 1:**  \nDetected rotated license plate with oriented bounding boxes.  \n![Example 1](https://i.postimg.cc/kGc4yRVT/419f8a15e8c72891-jpg-rf-f35f2e7ce0b5f68e3a67983a520cb5db.jpg)  \n\n**Example 2:**  \nLicense plate detected with high accuracy.  \n![Example 2](https://i.postimg.cc/6qmswBF9/b1610b49fdc8767a2-jpg-rf-31acbba2f162344db41abcf2565bcb80.jpg)  \n\n**Example 3:**  \nDetection of multiple plates within a single image.  \n![Example 3](https://i.postimg.cc/NMjP0W6L/uovneg34ahma1-jpg-rf-6b9fb846eff1bcc0db562de9b946ca2f.jpg)  \n\n**Example 4:**  \nAnother example of a detected license plate with accurate bounding box positioning.  \n![Example 4](https://i.postimg.cc/GtG3m7n8/m417sncy6eda1-jpg-rf-5ecd2be865a84aee67271a8443af1f2d.jpg)  \n\n---\n\n## ⚙️ **Project Workflow**  \n\n1. **Dataset Preparation**  \n   - Downloaded and preprocessed the dataset from **Roboflow**.  \n\n2. **Model Training**  \n   - Trained the YOLOv8 model in a Kaggle GPU environment.  \n   - Saved the trained model weights as `best.pt`.  \n\n3. **Inference**  \n   - Performed inference using the trained model on test images.  \n   - Saved results as annotated images and bounding box coordinates and rotated angle details.  \n\n4. **Flask API**  \n   - Built APIs to handle image uploads and run the YOLOv8 model for real-time inference.  \n\n---\n\n## 🚀 **Getting Started**  \n\n### 1. Clone the Repository  \n```bash\ngit clone https://github.com/Ankitjha2202/object_detection_services.git\ncd object_detection_services\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fankitjha2202%2Fobject_detection_services","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fankitjha2202%2Fobject_detection_services","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fankitjha2202%2Fobject_detection_services/lists"}