{"id":22169463,"url":"https://github.com/aleksavukadinovic/digiteye","last_synced_at":"2025-10-12T19:30:34.607Z","repository":{"id":264082642,"uuid":"892275388","full_name":"AleksaVukadinovic/DigitEye","owner":"AleksaVukadinovic","description":"A Python and TensorFlow-powered neural network for recognizing handwritten digits with precision.","archived":false,"fork":false,"pushed_at":"2024-11-28T10:24:08.000Z","size":4451,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-05T18:22:01.002Z","etag":null,"topics":["ai","artificial-intelligence","artificial-neural-networks","image-recognition","keras-tensorflow","neural-network","neural-networks","tensorflow"],"latest_commit_sha":null,"homepage":"","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/AleksaVukadinovic.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":"2024-11-21T20:13:50.000Z","updated_at":"2024-12-03T20:53:46.000Z","dependencies_parsed_at":"2024-11-22T09:02:41.159Z","dependency_job_id":null,"html_url":"https://github.com/AleksaVukadinovic/DigitEye","commit_stats":null,"previous_names":["aleksavukadinovic/digiteye"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AleksaVukadinovic/DigitEye","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AleksaVukadinovic%2FDigitEye","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AleksaVukadinovic%2FDigitEye/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AleksaVukadinovic%2FDigitEye/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AleksaVukadinovic%2FDigitEye/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AleksaVukadinovic","download_url":"https://codeload.github.com/AleksaVukadinovic/DigitEye/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AleksaVukadinovic%2FDigitEye/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279012668,"owners_count":26085159,"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","status":"online","status_checked_at":"2025-10-12T02:00:06.719Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["ai","artificial-intelligence","artificial-neural-networks","image-recognition","keras-tensorflow","neural-network","neural-networks","tensorflow"],"created_at":"2024-12-02T06:32:27.366Z","updated_at":"2025-10-12T19:30:34.252Z","avatar_url":"https://github.com/AleksaVukadinovic.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DigitEye\n\nThis project implements a neural network using TensorFlow and Keras to recognize handwritten digits from the MNIST dataset. The model can also predict custom handwritten digit images.\n\n---\n\n## Features\n- **Customizable Neural Network:** Dynamically set the number of layers, neurons, activation functions, and epochs.\n- **Data Augmentation:** Increases the training dataset using techniques like rotation, shifting, and zooming to improve generalization.\n- **Custom Predictions:** Load your custom digit images and let the model predict them.\n- **Model Saving and Loading:** Train a new model or load an existing one.\n\n---\n\n## Installation\n\n### Prerequisites\n- Python 3.x\n- TensorFlow\n- NumPy\n- OpenCV\n- Matplotlib\n\nInstall the required libraries with:\n\n```bash\npip install tensorflow numpy opencv-python matplotlib\n```\n\nNote for Linux users:\nIt is recommended to create a virtual environment to install these libraries, as direct pip installation may lead to system-wide conflicts. Use the following commands to set up a virtual environment:\n\n```bash\npython3 -m venv digit_eye_env\nsource digit_eye_env/bin/activate\npip install tensorflow numpy opencv-python matplotlib\n```\n\n## Usage\n1. Clone the repository\n```bash\ngit clone https://github.com/AleksaVukadinovic/DigitEye\ncd DigitEye\n```\n\n2. Run the script\n```bash\npython digit_recognition.py\n```\n\n3. Follow the console prompts\n\n## Materials Used\n\nThis project draws inspiration from and builds upon the following resources:\n\n- [DeepLearning Series by 3Blue1Brown](https://www.youtube.com/watch?v=aircAruvnKk\u0026list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi)  \n  An excellent visual introduction to the concepts behind neural networks and deep learning.\n\n- [Handwritten Digit Recognition by NeuralNine](https://youtu.be/bte8Er0QhDg?si=Nf-ChxRHdiWNV2M0)  \n  A practical guide to implementing a digit recognition system.\n\n- [Veštačka inteligencija (Artificial Intelligence)](https://poincare.matf.bg.ac.rs/~janicic//books/VI_B5.pdf)  \n  A comprehensive textbook by Mladen Nikolić and Predrag Janičić, providing theoretical insights into artificial intelligence.\n\n- [Using Neural Networks to Recognize Digits](http://neuralnetworksanddeeplearning.com/chap1.html)  \n  A detailed article explaining the mathematics and algorithms behind digit recognition using neural networks.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faleksavukadinovic%2Fdigiteye","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faleksavukadinovic%2Fdigiteye","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faleksavukadinovic%2Fdigiteye/lists"}