EdgeInfoAsObject Object Detection Dataset and Pre-Trained Model by USMCMIRC

Images

3684 images

Explore Dataset

Here are a few use cases for this project:

Film Classification and Cataloging: This model could be used by libraries, universities, film enthusiasts or movie databases who have large collections of film materials. The system could classify the films by the information present on the film edges (like manufacturer, type of film, date, etc) and create a corresponding metadata which would help in easier searching and sorting of the film materials.
Authentication and Verification: Film collectors and auction houses could use this model to verify the authenticity of the film reels, by detecting and analyzing the specific marks or names present on the edges of the film reels.
Restoration and Conservation: Museums and film archives could apply the computer vision model during film restoration projects to identify important characteristics about the film, such as its manufacturer and type, which are crucial information for the appropriate conservation procedures.
Film Production Tracking: Film production companies might use this model to track old movie reels or sample works stored in their archives. By identifying the edge information, they can classify each film reel with specific data, improving their inventory process.
Study of Film History: It can be used for studies about the history and development of film technology. By identifying the different manufacturers and types of film from various time periods, the model can provide valuable information about the evolution of film over time.

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{
                            edgeinfoasobject_dataset,
                            title = { EdgeInfoAsObject Dataset },
                            type = { Open Source Dataset },
                            author = { USMCMIRC },
                            howpublished = { \url{ https://universe.roboflow.com/usmcmirc/edgeinfoasobject } },
                            url = { https://universe.roboflow.com/usmcmirc/edgeinfoasobject },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2023 },
                            month = { jul },
                            note = { visited on 2024-04-28 },
                            }