{"id":24647440,"url":"https://github.com/deepaksilaych/vehicle_number_plate_detection","last_synced_at":"2025-04-03T15:47:57.860Z","repository":{"id":260695062,"uuid":"881992875","full_name":"DeepakSilaych/vehicle_number_plate_detection","owner":"DeepakSilaych","description":null,"archived":false,"fork":false,"pushed_at":"2024-11-01T21:31:45.000Z","size":282767,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-09T04:41:08.022Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/DeepakSilaych.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":"2024-11-01T16:45:37.000Z","updated_at":"2024-11-01T21:31:52.000Z","dependencies_parsed_at":"2024-11-01T22:34:37.568Z","dependency_job_id":null,"html_url":"https://github.com/DeepakSilaych/vehicle_number_plate_detection","commit_stats":null,"previous_names":["deepaksilaych/vehicle_number_plate_detection"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepakSilaych%2Fvehicle_number_plate_detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepakSilaych%2Fvehicle_number_plate_detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepakSilaych%2Fvehicle_number_plate_detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepakSilaych%2Fvehicle_number_plate_detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepakSilaych","download_url":"https://codeload.github.com/DeepakSilaych/vehicle_number_plate_detection/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247033156,"owners_count":20872521,"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":[],"created_at":"2025-01-25T15:49:05.113Z","updated_at":"2025-04-03T15:47:57.837Z","avatar_url":"https://github.com/DeepakSilaych.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Vehicle Number Plate Detection\n\nA project to detect vehicle number plates using computer vision techniques. This pipeline employs traditional image processing, selective search, and custom filtering to identify regions of interest in an image.\n\n## Features\n- Detects license plates in various orientations (horizontal and rotated)\n- Filters candidates based on aspect ratio, color, and edge density\n- Handles images taken from different angles for robustness\n\n## Table of Contents\n- [Installation](#installation)\n- [Usage](#usage)\n- [Methodology](#methodology)\n- [Results](#results)\n- [Challenges and Limitations](#challenges-and-limitations)\n- [Future Improvements](#future-improvements)\n- [License](#license)\n\n## Installation\n\n1. Clone the repository:\n    ```bash\n    git clone https://github.com/deepaksilaych/number-plate-detection.git\n    cd number-plate-detection\n    ```\n\n2. Install the required libraries:\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n## Usage\n\n1. Run the main script to detect number plates in a sample image:\n    ```bash\n    python src/main.py --image_path path_to_your_image.jpg\n    ```\n\n2. For interactive exploration, open the Jupyter notebook:\n    ```bash\n    jupyter notebook notebooks/Number_Plate_Detection.ipynb\n    ```\n\n## Methodology\n\nThis pipeline consists of several steps to process images and detect license plates effectively:\n\n1. **Preprocessing**:\n    - Converts images to grayscale.\n    - Resizes and applies Gaussian blur for noise reduction.\n\n2. **Selective Search**:\n    - Proposes candidate regions that might contain license plates using selective search.\n\n3. **Candidate Filtering**:\n    - **Aspect Ratio and Area Filtering**: Filters regions based on aspect ratios and sizes typical for license plates.\n    - **Color Filtering**: In HSV color space, filters for regions predominantly white or yellow (common license plate backgrounds).\n    - **Edge Density Filtering**: Retains regions with moderate edge density, often indicative of text-heavy regions like license plates.\n\n4. **Rotation Handling**:\n    - The image is processed at multiple angles to handle rotated plates.\n    - Detected regions are transformed back to the original orientation.\n\n## Results\n\nThe detection pipeline has shown effective results in detecting both horizontally aligned and rotated license plates. \n\u003c!-- Below are some sample outputs:\n\n![Example 1](data/example_output1.jpg)\n![Example 2](data/example_output2.jpg) --\u003e\n\n## Challenges and Limitations\n\n- **False Positives**: Similar-looking regions may be mistakenly identified as license plates.\n- **Lighting Conditions**: Varying lighting or shadow conditions can impact detection accuracy.\n- **Rotation and Filtering**: The rotation-based approach can be computationally expensive.\n\n## Future Improvements\n\n- **Integrate OCR**: Implement optical character recognition (OCR) to read text on detected plates.\n- **Real-Time Processing**: Optimize the pipeline to allow for real-time processing.\n- **Reduce False Positives**: Consider machine learning models or deep learning-based detection to improve accuracy and reduce false positives.\n\n\u003c!-- ## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. --\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepaksilaych%2Fvehicle_number_plate_detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepaksilaych%2Fvehicle_number_plate_detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepaksilaych%2Fvehicle_number_plate_detection/lists"}