Wait, you want a picture of my poop? Really?

Yes, we do! Duke researchers are developing a method to automatically categorize human feces from images as a means of advancing individual health.

In order to develop the algorithm, we need images of all kinds of human feces. A LOT of images. Everybody is different and our differences will ensure a robust algorithm. If you are over the age of 18 and a resident of the United States, and would like to advance this scientific research, please upload a photo of your poop in a toilet bowl to our secure servers.

For the first batch of pictures used in the development of an algorithm to automatically categorize human feces, we used photos contributed through this study in combination with public images available online. We continue to accept images, and rest assured, your submission will be anonymous. You can submit as many times as you like. Thank you for contributing!

Study Terms & Image Upload


Sonia Grego, Claire M. Welling, Graham H. Miller, Peter F. Coggan, Katelyn L. Sellgren, Brian T. Hawkins, Geoffrey S. Ginsburg, Jose R. Ruiz, Deborah A. Fisher, and Brian R. Stoner. "A hands-free stool sampling system for monitoring intestinal health and disease." Scientific Reports 12, no. 1 (2022).

Claire Welling, David R. Singleton, Steven B. Haase, Christian H. Browning, Brian R. Stoner, Claudia K. Gunsch, and Sonia Grego. "Predictive values of time-dense SARS-CoV-2 wastewater analysis in university campus buildings." Science of The Total Environment (2022): 155401.

Sonia Grego, Jin Zhou, Krishnendu Chakrabarty, Brian R. Stoner, Jose R. Ruiz, Deborah A. Fisher. "Automated Stool Image Analysis for Artificial Intelligence in a Smart Toilet." Gastroenterology 160 (May 2021).

Jin Zhou, Nick DeCapite, Jackson McNabb, Jose R. Ruiz, Deborah A. Fisher, Sonia Grego, Krishnendu Chakrabarty.  "Stool Image Analysis for Precision Health Monitoring by Smart Toilet." Proceedings of Machine Learning Research 149 (2021).