Other Projects

1. DIPimage and DIPlib
   Cris Luengo
   Partners: Bernd Rieger, Lucas van Vliet, Quantitative Imaging Group, Delft University of Technology, The Netherlands; Michael van Ginkel, Unilever Research and Development, Colworth House, Bedford, UK
   Funding: S-faculty, SLU
   Period: 0807-
   Abstract: DIPimage is a MATLAB toolbox for scientific image analysis, useful for both teaching and research. It has been in active development since 1999, when it was created at Delft University of Technology. In 2008, when Cris Luengo moved to Uppsala, CBA was added to the project as a main development site. DIPlib, created in 1995, is a C library containing many hundreds of image analysis routines. DIPlib is the core of the DIPimage toolbox, and both projects are developed in parallel. Because DIPlib provides efficient algorithms, MATLAB is useful for image analysis beyond the prototyping stage. Together, MATLAB and DIPimage form a powerful tool for working with scalar and vector images in any number of dimensions.

2. Animal Rules of Motion
   Cris Luengo
   Partners: David Sumpter, Andrea Perna, Daniel Strömbom, Richard Mann, Dept. of Mathematics, UU
   Funding: S-faculty, SLU
   Period: 0902-
   Abstract:  Group animals, such as fish, prawns and ants, move based on a set of relatively simple rules. Out of these simple rules, complex group dynamics emerge. Mathematical models, constructed to understand this group behaviour, need to be fitted to observation data. We apply image analysis techniques to automatically obtain position, direction and speed, as well as other movement parameters, from video recordings of such animals in controlled experimental environments.

3. Tracking Honey Bees and Their Interactions
   Cris Luengo
   Partners: Olle Terenius, Ingemar Fries, Joachim Rodrigues de Miranda, Eva Forsgren, Barbara Locke, Dept. of Ecology, SLU; Fredrik Liljeros, Dept. of Sociology, Stockholm University
   Funding: Åke Wiberg foundation
   Period: 1003-
   Abstract:  In this project, we intend to set up a system in which we can observe a portion of a bee hive (containing several hundred individuals, each tagged with a number on its back) over days or weeks. Bees will be free to enter and exit the hive, and the environment will be set up to provide them with an environment that is as natural as possible. The purpose is to observe the natural behaviour of the bees, and record the type and duration of interaction between individuals. In 2010 Olle Terenius was awarded a small grant from the Åke Wiberg foundation for materials and consumables, which we will use to create a setup and obtain preliminary data for a larger grant application.

4. Image Analysis for Studying Horse Behavior
   Anders Brun
   Partners: Lars Roepstorff, Anna Byström, SLU
   Funding: S-faculty, Dept.  of Equine Studies, SLU
   Period: 0901-
   Abstract: In this project, we track the hoof of the horse, filmed with high-speed cameras, when it hits the ground after a jump. We also analyze signals from a pressure sensor on the saddle. The work of CBA is mainly to help the veterinary group to analyze these signals. During 2010 we have mainly designed novel algorithms for the analysis of saddle pressure using PCA.

5. Optical Character Recognition of Handwritten Texts
   Anders Brun, Ewert Bengtsson
   Partners: Jonas Lindström Dept. of History; Bengt Dahlqvist Dept. of Linguistics and Philology
   Funding: Faculty of Languages and Humanities, UU
   Period: 1008-
   Abstract: Optical Character Recognition is still, after nearly 100 years of research, an active area of research. Currently one of the frontiers is the recognition of handwritten text, in particular from historical documents. During 2010 the findings of this project were published in a short report about current state-of-the-art algorithms in OCR. Some pilot studies were also performed. The project is now working towards a major grant application to create a centre for handwritten document recognition.