handheld augmented reality

Augmented Reality Anywhere and Anytime   


   Social Augmented Reality

   Information Presentation

   Real-Time Self Localization

   Structural Modelling

   AR Graphics

   AR Navigation

   Augmented Reality Games

   Past Projects



   Hybrid SLAM

   Panorama SLAM

   Planar SLAM

   Model-Based Tracking

   Marker-Based Tracking


Software Libraries

   Studierstube ES

   Studierstube Tracker










   Student projects


   Site map


The Handheld Augmented Reality
Project is supported by the
following institutions:



Christian Doppler Forschungsgesellschaft


Graz University of Technology




Come to ISMAR 2011



Follow us on twitter

Pill Recognition

Project Description

In late 2008 a Master thesis project was started to create an application for online segmentation and recognition of medicals on a mobile phone. The application should help medical stuff in recognizing unknown medicals, especially when treating patients in home care.

The application is heavily based on computer vision algorithms for segmentation of pills. Features for recognition of medicals include the color, shape, and the approximate size amongst others.

Graphical User Interface

A graphical user interface allows a convenient way for controlling the application.

On startup, the special target is detected, the
individual pills are segmented and their shape
and size are estimated.

Each individual pill can be selected, and detailed
information is given.


After querying the remote database and fetching
the results, detailed descriptions about the pills
are shown, including a sample picture of a
possible match for visual verification.

Finally the program is terminated.

Project Status

The application was developed on a standard desktop computer, and is currently ported to mobile phones. The algorithms are still under development, as well as the technical documentation is currently being written.

Project Team

Design and Implementation: Andreas Hartl

Supervision: Clemens Arth, Daniel Wagner


copyright (c) 2014 Graz University of Technology