{"id":28056472,"url":"https://github.com/r4f405/mnist-number-recognition-python","last_synced_at":"2025-08-06T08:14:30.126Z","repository":{"id":287787434,"uuid":"965785689","full_name":"R4F405/mnist-number-recognition-python","owner":"R4F405","description":"This project implements a handwritten digit recognizer using a model trained on the MNIST dataset.","archived":false,"fork":false,"pushed_at":"2025-05-06T13:26:18.000Z","size":1099,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-06T14:43:00.962Z","etag":null,"topics":["matplotlib","mnist-classifier","mnist-dataset","mnist-handwriting-recognition","mnist-image-dataset","numpy-python","pillow","pillow-library","python","python3","scipy","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/R4F405.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,"zenodo":null}},"created_at":"2025-04-13T22:29:45.000Z","updated_at":"2025-05-06T13:28:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"fad1c632-fec8-42c3-b2ae-c8c4001ada95","html_url":"https://github.com/R4F405/mnist-number-recognition-python","commit_stats":null,"previous_names":["r4f405/reconocimiento-de-digitos-mnist","r4f405/mnist-number-recognition-python"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/R4F405%2Fmnist-number-recognition-python","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/R4F405%2Fmnist-number-recognition-python/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/R4F405%2Fmnist-number-recognition-python/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/R4F405%2Fmnist-number-recognition-python/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/R4F405","download_url":"https://codeload.github.com/R4F405/mnist-number-recognition-python/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253692388,"owners_count":21948316,"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":["matplotlib","mnist-classifier","mnist-dataset","mnist-handwriting-recognition","mnist-image-dataset","numpy-python","pillow","pillow-library","python","python3","scipy","tensorflow"],"created_at":"2025-05-12T07:00:22.320Z","updated_at":"2025-05-12T07:00:23.462Z","avatar_url":"https://github.com/R4F405.png","language":"Python","readme":" # MNIST Digit Recognition ✍️🔢\n\n[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)\n[![Python: 3.8+](https://img.shields.io/badge/Python-3.8%2B-blue.svg?logo=python\u0026logoColor=white)](https://www.python.org/downloads/release/python-380/)\n\nThis project implements a handwritten digit recognizer using a model trained on the MNIST dataset. The system can process images of digits, center them appropriately, and predict which number they represent.\n\n## 💡 Description\n\nThis program uses a neural network trained with the MNIST dataset to recognize handwritten digits. Main features:\n\n- Image processing to adapt them to the MNIST format (28x28 pixels)\n- Automatic digit centering based on the center of mass\n- Image normalization and binarization\n- Prediction using a pre-trained model\n\n## ✅ Requirements\n\n- Python 3.8 or higher\n- TensorFlow\n- NumPy\n- Matplotlib\n- PIL (Pillow)\n- SciPy\n\nYou can install the dependencies with:\n\n```bash\npip install tensorflow numpy matplotlib pillow scipy\n```\n\n## 📁 Project Structure\n\n```\n.\n├── modelo_mnist.keras    # Pre-trained TensorFlow model\n├── numero.png            # Example image to predict\n└── Reconocer_Numeros.py  # Main script\n```\n\n## ▶️ Usage\n\n1.  Place an image of a handwritten digit named `numero.png` in the project directory.\n2.  Make sure the pre-trained model `modelo_mnist.keras` is in the directory.\n3.  Run the script:\n\n```bash\npython Reconocer_Numeros.py\n```\n\nThe program will display the processed image and the digit prediction.\n\n## ⚙️ How it Works\n\nThe script performs the following operations:\n\n1.  Loads and processes the image:\n    * Converts to grayscale\n    * Inverts colors (assumes white background, black digit)\n    * Resizes to 28x28 pixels\n    * Binarizes the image\n    * Normalizes values between 0 and 1\n    * Centers the digit based on its center of mass\n\n2.  Loads the pre-trained model with TensorFlow.\n\n3.  Performs digit prediction and displays the result.\n\n## 🎨 Customization\n\nTo use another image, simply change the `ruta_imagen` variable in the code or modify the file to accept command-line arguments.\n\n## 📜 License\n\nThis project is under the GNU General Public License v3.0. See the [LICENSE](LICENSE) file for more details.\n\n## 👨‍💻 Author\n\nR4F405\n\n[LinkedIn](https://www.linkedin.com/in/rafaspg) · [GitHub](https://github.com/R4F405)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr4f405%2Fmnist-number-recognition-python","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fr4f405%2Fmnist-number-recognition-python","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr4f405%2Fmnist-number-recognition-python/lists"}