Skip Navigation Bar
NLM logo

NLM Announces Pill Image Recognition Challenge Winners

August 1, 2016

NLM hosted a Pill Image Recognition Challenge as part of its research and development in Computational Photography Project for Pill Identification (C3PI). Teams participating in the challenge submitted algorithms and software that will contribute to the creation of a system that can match photos taken by a smart phone to the NLM RxIMAGE database of high-resolution prescription pill images. This new system can give consumers a simple way to recognize mystery pills, help prevent unnecessary medication errors, and reduce waste by identifying pills that might otherwise be discarded.

The Pill Image Recognition Challenge responds to the increase in prescription pill use, the increased need for prescription pill management, and the challenges the public faces in the changing look of prescription pills.

Listen to Michael J. Ackerman, lead of the Pill Image Recognition Challenge, talk about what led to the challenge:

Keyboard controls: Space bar - toggle play/pause; Right and Left Arrow - seek the video forwards and back; Up and Down Arrow - increase and decrease the volume; M key - toggle mute/unmute; F key - toggle fullscreen off and on.

Video Transcript

If your browser doesn't support javascript, you can download the mp4 files 1080p, 720p, or 480p directly as well as the caption file Ackerman_Pill_ID_Video20160801.vtt

The winners of the Pill Image Recognition Challenge are listed below. Winners were determined by mean average precision (MAP) of the submitted computer vision algorithm. The eligible submission with the highest MAP score was recommended as the first place winner, with the next two best MAP scores respectively recommended for second and third place. Winners used deep learning to achieve their results, opening new possibilities in pill image recognition for researchers.

First prize: MSU Mobile Pill Finder
Team captain: Mi Zhang, PhD
Assistant Professor, Department of Electrical and Computer Engineering, College of Engineering
Team members: Xiao Zeng, Department of Electrical and Computer Engineering
Kai Cao, PhD, Department of Computer Science and Engineering
Michigan State University

Second prize:  CASTELO (Completely Automated System to Elucidate Lozenge Origin)
Team captain: Michael Solomon
Team members: Greg Sadetsky, Ann-Julie Rhéaume

Third prize: Nikolay Khatuntsev
Pleasanton, California

The Pill Image Recognition Challenge was a National Institutes of Health (NIH) Challenge under the America COMPETES (Creating Opportunities to Meaningfully Promote Excellence in Technology, Education, and Science) Reauthorization Act of 2010 (Pub. L. 111-358).


The National Library of Medicine (NLM) is a leader in research in biomedical informatics and data science and the world’s largest biomedical library. NLM conducts and supports research in methods for recording, storing, retrieving, preserving, and communicating health information. NLM creates resources and tools that are used billions of times each year by millions of people to access and analyze molecular biology, biotechnology, toxicology, environmental health, and health services information. Additional information is available at

Last Reviewed: December 6, 2019