{"id":19871650,"url":"https://github.com/samir-atra/license-plate-recognition","last_synced_at":"2026-05-03T17:32:08.483Z","repository":{"id":44326058,"uuid":"292061704","full_name":"Samir-atra/license-plate-recognition","owner":"Samir-atra","description":"License plate recognition system ","archived":false,"fork":false,"pushed_at":"2024-08-16T22:13:22.000Z","size":274,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-30T08:04:41.467Z","etag":null,"topics":["imageai-library","knn","lpr","numpy","object-detection","opencv","python","tensorflow","tensorflow-tutorials"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Samir-atra.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2020-09-01T17:19:44.000Z","updated_at":"2024-08-16T22:13:25.000Z","dependencies_parsed_at":"2025-01-11T16:32:43.622Z","dependency_job_id":"b954d677-3b98-4c52-91a5-6a0ed6a676bb","html_url":"https://github.com/Samir-atra/license-plate-recognition","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Samir-atra/license-plate-recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Samir-atra%2Flicense-plate-recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Samir-atra%2Flicense-plate-recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Samir-atra%2Flicense-plate-recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Samir-atra%2Flicense-plate-recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Samir-atra","download_url":"https://codeload.github.com/Samir-atra/license-plate-recognition/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Samir-atra%2Flicense-plate-recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32578578,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T06:36:36.687Z","status":"ssl_error","status_checked_at":"2026-05-03T06:36:09.306Z","response_time":103,"last_error":"SSL_read: 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":["imageai-library","knn","lpr","numpy","object-detection","opencv","python","tensorflow","tensorflow-tutorials"],"created_at":"2024-11-12T16:13:05.123Z","updated_at":"2026-05-03T17:32:08.478Z","avatar_url":"https://github.com/Samir-atra.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# License Plate Recognition\n\nThis repository contains two implementations of a License Plate Recognition (LPR) system. The first, `OldLPR(2018)`, is a traditional computer vision approach using OpenCV. The second, `LPR`, is a more modern approach using deep learning with TensorFlow and ImageAI.\n\n## LPR (2023)\n\nThis is a more recent implementation of a license plate recognition system using modern deep learning techniques. It is built to be integrated into a camera system for real-time detection and classification of license plates.\n\n### Technology Stack\n\n*   **Python 3**\n*   **TensorFlow/Keras**\n*   **ImageAI:** A library for object detection and image classification.\n*   **Jupyter Notebook:** The code is provided as a notebook for easy experimentation.\n*   **OpenCV**\n*   **Numpy**\n\n### Methodology\n\nThe model consists of two main parts:\n\n1.  **License Plate Detection:** A YOLOv3 object detection model, trained using the ImageAI library, is used to detect and locate license plates in an image.\n2.  **Character Recognition:** A Recurrent Neural Network (RNN) is used to process the cropped license plate image as a time series of characters. This is an experimental approach to recognize the characters on the plate.\n\n### Dataset\n\n*   **License Plate Detection:** [Car Plate Detection dataset on Kaggle](https://www.kaggle.com/datasets/andrewmvd/car-plate-detection)\n*   **Character Recognition:** [Characters Dataset for License Plate Recognition on Kaggle](https://www.kaggle.com/datasets/sahajap99/characters-dataset-for-license-plate-recognition)\n\n### Usage\n\nThe code is located in the `LPR/` directory as a Jupyter Notebook (`LPR.ipynb`). It is designed to be run in a Google Colab environment.\n\n**Note:** The notebook has a dependency on Google Drive for loading the dataset and saving models. You will need to mount your Google Drive and adjust the file paths accordingly.\n\n## OldLPR (2018)\n\nThis is an older implementation of a license plate recognition system built with traditional computer vision techniques.\n\n### Technology Stack\n\n*   **Python 2**\n*   **OpenCV:** Used for image processing and computer vision tasks.\n*   **Numpy:** For numerical operations.\n\n### Methodology\n\nThe system follows these steps:\n\n1.  **Plate Detection:** The system detects license plates by finding contours in the image that could be characters. It then groups these characters to identify potential license plates.\n2.  **Character Recognition:** A K-Nearest Neighbors (KNN) classifier is used to recognize the characters on the detected license plate. The KNN model is trained on pre-classified character images.\n\n### Usage\n\nThe main script is `OldLPR(2018)/Main (1).py`. To run the script, you will need the following files in the same directory:\n\n*   `classifications.txt`: Contains the classifications for the training data.\n*   `flattened_images.txt`: Contains the flattened image data for training the KNN model.\n\nThe script is written in Python 2.\n\n## Future Work\n\nA potential improvement would be to build a single, end-to-end model that combines both license plate detection and character recognition. This could be achieved by using two object detection models:\n\n1.  The first model would detect and crop the license plate from the image.\n2.  The second model would detect and classify the characters from the cropped plate image.\n\n## License\n\nThis project is licensed under the terms of the license agreement. See the [LICENSE](LICENSE) file for more details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamir-atra%2Flicense-plate-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsamir-atra%2Flicense-plate-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamir-atra%2Flicense-plate-recognition/lists"}