{"id":23554313,"url":"https://github.com/arcticray/crack-detection","last_synced_at":"2025-07-13T08:37:22.944Z","repository":{"id":267312878,"uuid":"895768892","full_name":"ArcticRay/crack-detection","owner":"ArcticRay","description":"A python machine learning project aimed at automatically identifying cracks on concrete surface images using a Convolutional Neural Network.","archived":false,"fork":false,"pushed_at":"2025-02-03T16:38:45.000Z","size":560,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-15T19:13:35.034Z","etag":null,"topics":["cnn-classification","python"],"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/ArcticRay.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,"zenodo":null}},"created_at":"2024-11-28T21:35:45.000Z","updated_at":"2025-02-03T16:38:49.000Z","dependencies_parsed_at":"2024-12-09T16:51:19.533Z","dependency_job_id":"0bccf83f-cb94-4c87-bdfb-e519c60693e4","html_url":"https://github.com/ArcticRay/crack-detection","commit_stats":{"total_commits":15,"total_committers":1,"mean_commits":15.0,"dds":0.0,"last_synced_commit":"ab651e4cecca358bfa889166638c2925d967704b"},"previous_names":["arcticray/crack-detection"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ArcticRay/crack-detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArcticRay%2Fcrack-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArcticRay%2Fcrack-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArcticRay%2Fcrack-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArcticRay%2Fcrack-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ArcticRay","download_url":"https://codeload.github.com/ArcticRay/crack-detection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArcticRay%2Fcrack-detection/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265110578,"owners_count":23712890,"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":["cnn-classification","python"],"created_at":"2024-12-26T12:13:55.154Z","updated_at":"2025-07-13T08:37:22.886Z","avatar_url":"https://github.com/ArcticRay.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Surface Crack Detection\n\n![Project Banner](outputs/sample_images.png)\n\n## 📄 Description\n\n**Surface Crack Detection** is a machine learning project aimed at automatically identifying cracks on surface images.\n\n**Confusion Matrix**\n\n![Project Banner](outputs/confusion_matrix.png)\n\n## 🚀 Features\n\n- **Data Preprocessing:** Loading, resizing, and normalizing images.\n- **Model Training:** Development and training of a CNN for image classification.\n- **Model Evaluation:** Assessing model performance with metrics and visualizations.\n- **Image Classification** Uploading and classifying\n- **Explainability (LIME):** Generating visual explanations showing which regions of an image the model relies on when predicting cracks.\n\n**Example LIME Explanation**  \nBelow is a sample visualization using LIME, highlighting important superpixels contributing to the “Positive” (crack) classification:\n\n![LIME Explanation](outputs/lime/lime_explanation.png)\n\n## Dataset\n\nThe dataset comprises images categorized into two classes:\n\n- **Positive:** Images containing surface cracks.\n- **Negative:** Images without surface cracks.\n\nÖzgenel, Çağlar Fırat (2019), “Concrete Crack Images for Classification”, Mendeley Data, V2,\n[doi: http://dx.doi.org/10.17632/5y9wdsg2zt.2x](https://data.mendeley.com/datasets/5y9wdsg2zt/2)\n\n\u003c!-- https://www.kaggle.com/datasets/arunrk7/surface-crack-detection\u003e\n\n\u003c!-- Ausführungsschritte\n    - source crack_env/bin/activate\n    - python3 src/data_preprocessing.py\n    - python3 src/eda.py\n    - python3 src/model.py\n    - python3 src/train.py\n    - python3 src/evaluate.py\n    - python3 src/predict.py test/TestCrack.jpeg\n    - python3 src/predict.py test/TestCrack2.jpg\n    - python3 src/explain.py test/TestCrack.jpeg\n\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farcticray%2Fcrack-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farcticray%2Fcrack-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farcticray%2Fcrack-detection/lists"}