{"id":23388987,"url":"https://github.com/ayberkgezer/car-damage-detection","last_synced_at":"2026-05-02T02:39:12.603Z","repository":{"id":162278883,"uuid":"579708044","full_name":"ayberkgezer/Car-Damage-Detection","owner":"ayberkgezer","description":null,"archived":false,"fork":false,"pushed_at":"2024-08-10T09:27:26.000Z","size":363,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-14T09:54:06.528Z","etag":null,"topics":["cnn-classification","deep-neural-networks","image-classification","image-processing","python","vgg16"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ayberkgezer.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}},"created_at":"2022-12-18T16:14:45.000Z","updated_at":"2024-08-10T09:27:29.000Z","dependencies_parsed_at":"2024-08-10T10:35:28.298Z","dependency_job_id":null,"html_url":"https://github.com/ayberkgezer/Car-Damage-Detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayberkgezer%2FCar-Damage-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayberkgezer%2FCar-Damage-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayberkgezer%2FCar-Damage-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayberkgezer%2FCar-Damage-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ayberkgezer","download_url":"https://codeload.github.com/ayberkgezer/Car-Damage-Detection/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247852256,"owners_count":21006915,"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","deep-neural-networks","image-classification","image-processing","python","vgg16"],"created_at":"2024-12-22T02:35:57.672Z","updated_at":"2026-05-02T02:39:12.564Z","avatar_url":"https://github.com/ayberkgezer.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Car Damage Detection on VGG-16\n\n[![(article)](https://img.shields.io/badge/Article-DOI%3A10.53608/estudambilisim.1421332.-B31B1B.svg)](https://dergipark.org.tr/en/pub/estudambilisim/issue/86200/1421332)\n\nFor this we used a CNN model, VGG16[[1]](https://arxiv.org/abs/1409.1556). We used our own dataset that we had prepared and trained the VGG16 model ourselves. Our study consisted of 4 main questions:\n\n- Is it a car?\n- Is there any damage on the car?\n- In which part of the car is the damage?\n- What is the level of damage?\n\nWe prepared and trained our own datasets within these 4 questions.\n\n## Data Sets\n\n| Data Sets                                   | Training | Validation |\n| :--------                                   | :------- | :--------- |\n| Is it a car?                                | `920`    | `230` |\n| Is there any damage on the car?             | `1840`   | `460` |\n| In which any part of the car is the damage? | `976`    | `171` |\n| What is the level of damage?                | `979`    | `171` |\n\nWe used our original dataset, which consists of a total of 5,757 photographs.\n\n\n\n## Is it a car?\n\n| Data Sets                                   | Training | Validation |\n| :--------                                   | :------- | :--------- |\n| Car                               | `920`    | `230` |\n\nThe result we will get here is only querying whether there is a car or not.\n\n## Is there any damage on the car?\n\n| Data Sets                                   | Training | Validation |\n| :--------                                   | :------- | :--------- |\n|   Damaged          | `920`    | `230` |\n|   Undamaged          | `920`    | `230` |\n\nWe have done this training in order to determine whether there is a similar damage at this stage and to continue with the other stages according to the result.\n\n## In which any part of the car is the damage?\n\n| Data Sets                                   | Training | Validation |\n| :--------                                   | :------- | :--------- |\n| Front                                | `418`    | `73` |\n| Rear                                | `287`    | `50` |\n| Side                                | `271`    | `48` |\n\nour aim here is to determine which part of the car the damaged area in the photo belongs to. We trained our parameters as front, back and side.\n\n## What is the level of damage?\n\n| Data Sets                                   | Training | Validation |\n| :--------                                   | :------- | :--------- |\n| Minor                                | `278`    | `48` |\n| Moderate                                | `315`    | `55` |\n| Severe                               | `386`    | `68` |\n\nNow that we know the damage is and where it is, it's up to us to separate the level of damage we set ourselves.\n\n## Accuracy Rating\n\n| Training                                    | Accuracy Rating |\n| :--------                                   | :-------        |\n| Is it a car?                                | %98             |\n| Is there any damage on the car?             | %90             |\n| In which any part of the car is the damage? | %70             |\n| What is the level of damage?                | %66             |\n\n![Accuracy Rating graph](https://i.hizliresim.com/4gqn2gn.png)\n\n## Result Exp\n\n![Result](https://i.hizliresim.com/15uh2nz.jpg)\n\n## License\n\n[![MIT License](https://img.shields.io/badge/License-MIT-green.svg)](https://choosealicense.com/licenses/mit/)\n\n## Authors\n\n- [@ayberkgezer](https://www.github.com/octokatherine)\n- [@TediTae](https://github.com/TediTae/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayberkgezer%2Fcar-damage-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fayberkgezer%2Fcar-damage-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayberkgezer%2Fcar-damage-detection/lists"}