aircraft_skin_defects Computer Vision Project

DDIISc

Updated 2 years ago

3.2k

views

162

downloads

Metrics

Try This Model

Drop an image or

browse your device

Description

This is a custom dataset created with manually clicked photographs of 3 different types of aircraft. The images are labelled for 5 different classes of surface defects on aircraft skin viz.

Crack Dent Scratch Paint-peel-off Missing-head (rivets, fastners, screws etc) The dataset consists of total 372 images with distribution as follows: Hawker Hunter - 276 HT2 - 70 Pushpak - 76

The dataset has been created for implementation as part of M.Tech (AI) thesis of the author at IISc, Bengaluru.

Note: The author couldn't find any detailed / relevant dataset available on the internet. Thus, this dataset is aimed as a repo of such images for future use as well. Please feel free to use it for your own custom model or you can use the pretrained model. Kindly cite requisite credits to the author while using it.

Use This Trained Model

Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.

Try In Browser Deploy Model

Build Computer Vision Applications Faster with Supervision

Visualize and process your model results with our reusable computer vision tools.

Cite This Project

LICENSE

CC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

                        @misc{
                            aircraft_skin_defects_dataset,
                            title = { aircraft_skin_defects Dataset },
                            type = { Open Source Dataset },
                            author = { DDIISc },
                            howpublished = { \url{ https://universe.roboflow.com/ddiisc/aircraft_skin_defects } },
                            url = { https://universe.roboflow.com/ddiisc/aircraft_skin_defects },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2023 },
                            month = { may },
                            note = { visited on 2024-12-31 },
                            }