Computer-Vision based Pharmaceutical Pill Recognition On Mobile Phones

• Robustness: Segmentation regardless of pill color using a credit-card-sized target
• Feature Estimation: Dimensions, shape, color (others on demand)
• Extensibility: Trainable to work with different objects

Note: The original project was designed at the end of my Master’s and the computer vision core was subsequently re-implemented along with custom tracking. Platforms: Windows, Linux, (OS X, iOS, Android, Unity plugin).

Publications:

• A. Hartl and C. Arth. “Computer-Vision based Pharmaceutical Pill Recognition on Mobile Phones”, Web proceedings of the Central European Seminar on Computer Graphics for Students (CESCG), 2010
  
• A. Hartl, C. Arth and D. Schmalstieg. “Instant Segmentation and Feature Extraction for Recognition of Simple Objects on Mobile Phones”, Proceedings of the Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010
• A. Hartl, C. Arth and D. Schmalstieg. “Instant Medical Pill Recognition on Mobile Phones”, Proceedings of the IASTED International Conference on Computer Vision, 2011