{"id":29223614,"url":"https://github.com/charlyhno-eng/raspberry-plate-recognition","last_synced_at":"2026-05-08T00:38:28.153Z","repository":{"id":299580561,"uuid":"1003445434","full_name":"Charlyhno-eng/raspberry-plate-recognition","owner":"Charlyhno-eng","description":"License plate detection by computer vision on raspberry (optimized resources) - Python - OpenCV - Tesseract","archived":false,"fork":false,"pushed_at":"2025-06-30T09:27:40.000Z","size":26124,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-30T10:24:12.972Z","etag":null,"topics":["opencv","python","raspberry-pi","tesseract-ocr","yolov8"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Charlyhno-eng.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,"zenodo":null}},"created_at":"2025-06-17T06:54:39.000Z","updated_at":"2025-06-30T09:27:43.000Z","dependencies_parsed_at":"2025-06-17T09:34:34.110Z","dependency_job_id":"1e2b2dd6-364d-4b58-b5a0-5cc17e4814be","html_url":"https://github.com/Charlyhno-eng/raspberry-plate-recognition","commit_stats":null,"previous_names":["charlyhno-eng/raspberry-plate-recognition"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Charlyhno-eng/raspberry-plate-recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charlyhno-eng%2Fraspberry-plate-recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charlyhno-eng%2Fraspberry-plate-recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charlyhno-eng%2Fraspberry-plate-recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charlyhno-eng%2Fraspberry-plate-recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Charlyhno-eng","download_url":"https://codeload.github.com/Charlyhno-eng/raspberry-plate-recognition/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Charlyhno-eng%2Fraspberry-plate-recognition/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263264651,"owners_count":23439257,"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":["opencv","python","raspberry-pi","tesseract-ocr","yolov8"],"created_at":"2025-07-03T05:05:35.811Z","updated_at":"2026-05-08T00:38:28.148Z","avatar_url":"https://github.com/Charlyhno-eng.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# raspberry-plate-recognition\n\nLicense plate detection using computer vision on Raspberry Pi (resource-optimized).\n\nThis project combines YOLOv8 for license plate detection and Tesseract OCR for text recognition. The system captures real-time video streams, detects license plates from the frames, and extracts the alphanumeric text printed on them.\n\nIt is designed to be compact and efficient enough to run on low-power devices such as the Raspberry Pi. The detection model can be optimized and exported to ONNX format for faster inference.\n\n#### Key Features\n\n- Lightweight and optimized for Raspberry Pi\n- Real-time plate detection and OCR (in my case EasyOCR)\n- Compatible with YOLOv8 / ONNX runtime\n\n#### Dataset\n\nThe model uses a publicly available dataset from Kaggle:\nhttps://www.kaggle.com/datasets/fareselmenshawii/license-plate-dataset\n\nThis dataset contains various license plate images suitable for vehicle detection and OCR model training. Additional datasets can be integrated for better generalization across countries or plate types.\n\n## Installation\n\n```bash\nsudo apt update\nsudo apt install tesseract-ocr\n```\n\n```bash\npython3 -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\n```\n\n## Usage\n\n```bash\npython3 -m venv venv\nsource venv/bin/activate\npython plate_detector_live.py\n```\n\nYou can also try running the ONNX-based version, which consumes less power and offers better performance on compatible devices. However, depending on your Raspberry Pi version, ONNX may not work reliably. If that happens, use the default version instead.\n\n---\n\n## Training Your Own Model\n\nIf you want to adapt the detection to other license plate formats or countries:\n\n- Collect or download a new dataset.\n- Train a YOLOv8 model using the ultralytics package.\n- Export the trained model to .pt or .onnx format.\n- Replace the model file in the project folder.\n\nExample :\n\n```bash\nyolo detect train data=dataset.yaml model=yolov8n.pt epochs=50 imgsz=640\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcharlyhno-eng%2Fraspberry-plate-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcharlyhno-eng%2Fraspberry-plate-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcharlyhno-eng%2Fraspberry-plate-recognition/lists"}