{"id":23301532,"url":"https://github.com/edwinabdonshayo/uno-recognition","last_synced_at":"2026-01-26T04:32:00.835Z","repository":{"id":261112462,"uuid":"882445300","full_name":"EdwinAbdonShayo/UNO-Recognition","owner":"EdwinAbdonShayo","description":"UNO Recognition Program. Using the CNN technology to train a dataset of UNO cards.","archived":false,"fork":false,"pushed_at":"2024-11-06T22:55:01.000Z","size":49342,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-28T04:31:22.220Z","etag":null,"topics":["cnn","dataset","gpu","keras","opencv","pillow","python","recognition","tensorflow","uno","unocards"],"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/EdwinAbdonShayo.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":"2024-11-02T19:46:36.000Z","updated_at":"2024-11-07T04:42:46.000Z","dependencies_parsed_at":"2025-02-13T04:37:55.238Z","dependency_job_id":null,"html_url":"https://github.com/EdwinAbdonShayo/UNO-Recognition","commit_stats":null,"previous_names":["edwinabdonshayo/uno-recognition"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/EdwinAbdonShayo/UNO-Recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdwinAbdonShayo%2FUNO-Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdwinAbdonShayo%2FUNO-Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdwinAbdonShayo%2FUNO-Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdwinAbdonShayo%2FUNO-Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EdwinAbdonShayo","download_url":"https://codeload.github.com/EdwinAbdonShayo/UNO-Recognition/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdwinAbdonShayo%2FUNO-Recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28766886,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-26T03:54:34.369Z","status":"ssl_error","status_checked_at":"2026-01-26T03:54:33.031Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["cnn","dataset","gpu","keras","opencv","pillow","python","recognition","tensorflow","uno","unocards"],"created_at":"2024-12-20T10:13:54.666Z","updated_at":"2026-01-26T04:32:00.805Z","avatar_url":"https://github.com/EdwinAbdonShayo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# UNO-Recognition\n\n\nThis repository contains code and resources for building an UNO card recognition model. The project includes image resizing, data preprocessing, model training, and a GUI application for recognizing UNO cards via file upload or live camera feed.\n\n## Repository Structure\n* `dataset`: A folder, dataset, that contains the UNO cards images.\n* `resizeImg.py`: Resizes images in the dataset to a target width, maintaining the original aspect ratio.\n* `dataset_preprocessor.py`: Applies augmentations and transformations to the images to create a richer dataset for training.\n* `train.py`: Defines and trains a convolutional neural network (CNN) model for UNO card classification.\n* `app.py`: Provides a GUI to predict UNO card classes using a pre-trained model, with options to select an image file or use a live camera feed.\n* `Model.keras` \u0026 `Model(2).keras`: trained models, products of `train.py`, to be used by `app.py`.\n## Getting Started\n### Prerequisites\n* Python 3.8 or later\n* Install required libraries with:\n\u003e bash code\n```\npip install tensorflow pillow opencv-python numpy tkinter\n```\n### Dataset\nUNO card images are stored in the `dataset` folder. Each class has its own subfolder, e.g., `dataset/Red_0`, `dataset/Yellow_Draw_2`, etc. The dataset folder will be utilized by `resizeImg.py` and `dataset_preprocessor.py` to create `UNO_dataset` which will store the augmented data.\n\n## Scripts Overview\n1. Image Resizing - `resizeImg.py`\n- This script resizes all images in the `dataset` directory to a target width of 540 pixels, preserving the aspect ratio. The aim is to reduce the dataset large size reducing the training workload.\n\n#### Usage:\n\n\u003e bash code\n```\npython resizeImg.py\n```\n2. Data Preprocessing - `dataset_preprocessor.py`\n- The script applies various transformations and augmentations to each image to enhance dataset variety, creating rotated, zoomed, and filtered versions of each image.\n\n#### Usage:\n\n\u003e bash code\n```\npython dataset_preprocessor.py\n```\n3. Model Training - `train.py`\n- This script defines, compiles, and trains a CNN model on the augmented images in the `UNO_dataset` directory. The model architecture includes several convolutional, pooling, and dropout layers to improve accuracy. The trained model will be saved as `Model.keras` in the project directory.\n\n#### Usage:\n\n\u003e bash code\n```\npython train.py\n```\n\n4. GUI Prediction App - `app.py`\n- A Tkinter GUI application allows you to predict UNO card classes by uploading an image file or using a live camera feed. The GUI displays the predicted card name on the screen.\n\n#### Usage:\n\n\u003e bash code\n```\npython app.py\n```\n* **Predict from File**: Allows you to select an image file from your computer and display the prediction.\n* **Predict from Camera**: Uses the live camera feed to recognize UNO cards in real-time.\n\n## Credits\n\nThis project was developed by a team of three contributors:\n\n* \u003ca href=\"https://github.com/saki3110\"\u003eSakina Taygaully\u003ca\u003e\n* \u003ca href=\"https://github.com/gt663\"\u003eHans Nursing\u003ca\u003e\n* \u003ca href=\"https://github.com/EdwinAbdonShayo\"\u003eEdwin Shayo\u003ca\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedwinabdonshayo%2Funo-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fedwinabdonshayo%2Funo-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedwinabdonshayo%2Funo-recognition/lists"}