To submit an image for analysis the user can either provide its URL or upload a local copy of it from their machine. The supported image formats are .jpg, .png, .gif, .bmp, .webp, .tiff, .heic, .avif. Due to platform limitation the user should provide a direct link to the image and not link to a social media post. For more details on how to obtain the image URL, please refer to our guide on submitting images to the Image Inspector.
The analysis can take from a couple of seconds to a couple of minutes depending on the image size and the number of already submitted queries. The analysis results are stored in our server and if a user submits the same image the analysis results are returned directly without additional analysis.All image rights remain with the uploader, who is assumed to have the right to submit the image to the service for analysis.
Any feedback you may have on the web service is most welcome; please contact olgapapa@iti.gr
Acknowledgements
The User Interface of the Image Inspector is supported by the European Media and Information Fund. The synthetic image detection model was developed as part of our work in the Horizon Europe vera.ai project under Grant Agreement ID 101070093.
Relevant Publications
If you find the technologies demonstrated through this demo interesting or useful in your work, please cite the following papers:
Karageorgiou, D., Papadopoulos, S., Kompatsiaris, I., & Gavves, E. (2024). Any-Resolution AI-Generated Image Detection by Spectral Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Koutlis, C., & Papadopoulos, S. (2024, September). Leveraging representations from intermediate encoder-blocks for synthetic image detection. In the European Conference on Computer Vision(pp. 394-411). Cham: Springer Nature Switzerland.
Contributors
Symeon Papadopoulos, Senior Researcher (email: papadop@iti.gr)
Olga Papadopoulou, Research Associate (email: olgapapa@iti.gr)