Adhesion Object Detection Dataset and Pre-Trained Model by NED University

Images

511 images

Explore Dataset

Here are a few use cases for this project:

Quality Control in Manufacturing: FYP-CIS can be used to automatically inspect and identify defects in adhesion within various products during the manufacturing process. This helps manufacturers maintain a high level of quality assurance and reduce costs associated with product recalls and customer dissatisfaction.
Packaging Industry: The FYP-CIS model can be employed in the packaging industry to detect and prevent faulty adhesion in packaged products, such as bottles with improper sealing. This minimizes the risk of leakage, contamination, or tampering during transportation and storage.
Automotive Industry: FYP-CIS can be used to identify defects in the adhesion of automotive components, such as paint, coatings, and sealants, to ensure they meet safety and quality standards. This helps automobile manufacturers prevent long-term issues like corrosion, leaks, or part failure.
Medical Device Manufacturing: The FYP-CIS model can be applied to verify the adherence quality of medical devices and equipment, including prosthetics, implants, and various medical instruments. Proper adhesion is crucial in these devices to guarantee their intended function and maintain patient safety.
Construction Industry: FYP-CIS can be used to detect defects in the adhesion of materials such as paint, coatings, and sealants in buildings and infrastructure projects. Proper adhesion is necessary to ensure the longevity of the construction and avoid expensive repairs or premature failures.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite This Project

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

@misc{
                            adhesion-s0qyo_dataset,
                            title = { Adhesion Dataset },
                            type = { Open Source Dataset },
                            author = { NED University },
                            howpublished = { \url{ https://universe.roboflow.com/ned-university-vx4x6/adhesion-s0qyo } },
                            url = { https://universe.roboflow.com/ned-university-vx4x6/adhesion-s0qyo },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2023 },
                            month = { jun },
                            note = { visited on 2024-07-04 },
                            }