home  |   research   |  members   |  projects  |  publications   |  conferences of interest   |  downloads   |  contact  |  intern
 
 

Project Description

This is "The Multimedia Signal Processing and Security Lab", short WaveLab, website. We are a research group at the Computer Sciences Department of the University of Salzburg headed by Andreas Uhl. The short name "WaveLab" already indicates that wavelets are among our favorite tools - we have 15 years of experience in this area. Our research is focused on Multimedia Security including Watermarking, Image and Video Compression, Medical Image Classification, and Biometrics.
   

Endoscope Distortion Correction in (Texture Classification-based) Automated Diagnosis Support Systems (Undistort)

 

Project Description:

Undistort (FWF project 24366) is a project devoted to the investigation if knowledge about the type and extent of optical distortion in endoscopes can be exploited to improve the accuracy of texture-classification based automated diagnosis support systems. In particular, we focus on the gastrointestinal tract. We rely on datasets generated in earlier projects with Michael Häfner from the St. Elisabeth Hospital Vienna (colon data, aimed at polyp classification and cancer detection), and with Andreas Vecsei from the Vienna St. Anna Childrens Hospital (duodenal data, aimed at diagnosis of celiac disease).

 
 

Members:

 
 

Timeframe:

  • Feb 2012 - Jan 2015
 
 

Publications:

  1. [Gadermayr17a ] Degradation adaptive texture classification for real-world application scenarios Michael Gadermayr, Dorit Merhof, Andreas Vecsei, Andreas Uhl Pattern Recognition and Image Analysis 27:1, pp. 66-81, 2017
  2. [Gadermayr16b  ] Making texture descriptors invariant to blur Michael Gadermayr, Andreas Uhl EURASIP Journal on Image and Video Processing 2016:4, 2016
  3. [Gadermayr15b  ] Boosting Small-Data Performance of LBP: A Case Study in Celiac Disease Diagnosis Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of the 19th Scandinavian Conference on Image Analysis (SCIA'15), pp. 224-233, Springer LNCS, 9127, 2015
  4. [Gadermayr15c  ] How to Exploit Large Image Data in the Fields of Texture Classification Michael Gadermayr, Andreas Uhl In Proceedings of the IEEE International Conference on Image Processing (ICIP'15)2015, accepted
  5. [Gadermayr15a  ] Dealing with Intra-Class and Intra-Image Variations in Automatic Celiac Disease Diagnosis Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of Bildverarbeitung für die Medizin 2015 (BVM'15), pp. 461-466, March 2015
  6. [Gadermayr13e   ] Shape Curvature Histogram: A Shape Feature for Celiac Disease Diagnosis Michael Gadermayr, Michael Liedlgruber, Andreas Uhl, Andreas Vécsei In Medical Computer Vision. Large Data in Medical Imaging (Proceedings of the 3rd International MICCAI - MCV Workshop 2013), pp. 175-184, Springer LNCS, 8331, 2014
  7. [Gadermayr14i  ] Quality Based Information Fusion in Fully Automatized Celiac Disease Diagnosis Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of the German Conference on Pattern Recognition (GCPR'14), pp. 1-12, Springer LNCS, 8753, 2014
  8. [Gadermayr14h  ] Degradation Adaptive Texture Classification: A Case Study in Celiac Disease Diagnosis Brings new Insight Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of the International Conference on Image Analysis and Recognition (ICIAR'14), pp. 263-273, Springer LNCS, 8815, 2014
  9. [Gadermayr13f  ] Feature Extraction with Intrinsic Distortion Correction in Celiac Disease Imagery: No Need for Rasterization (Runner-up for Best Paper Award) Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Medical Computer Vision. Large Data in Medical Imaging (Proceedings of the 3rd International MICCAI - MCV Workshop 2013), pp. 196-204, Springer LNCS, 8331, 2014
  10. [Gadermayr14f  ] Degradation Adaptive Texture Classification Michael Gadermayr, Andreas Uhl In Proceedings of the IEEE International Conference on Image Processing 2014 (ICIP'14)Oct. 2014
  11. [Gadermayr14d  ] Scale-Adaptive Texture Classification Michael Gadermayr, Sebastian Hegenbart, Andreas Uhl In Proceedings of 22nd IEEE International Conference on Pattern Recognition (ICPR'14)Aug. 2014
  12. [Gadermayr14e  ] Is a Precise Distortion Estimation Needed for Computer Aided Celiac Disease Diagnosis? Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of the 8th International Conference on Image and Signal Processing (ICISP'14), pp. 620-628, Springer LNCS, 8509, July 2014
  13. [Gadermayr14a  ] The Effect of Endoscopic Lens Distortion Correction on Physicians' Diagnosis Performance Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of Bildverarbeitung für die Medizin 2014 (BVM'14), pp. 174-179, Aachen, Germany, Springer Informatik aktuell, March 2014
  14. [Gadermayr13d  ] Evaluation of Different Distortion Correction Methods and Interpolation Techniques for an Automated Classification of Celiac Disease Michael Gadermayr, Michael Liedlgruber, Andreas Uhl, Andreas Vécsei Computer Methods and Programs in Biomedicine 112:3, pp. 694-712, Dec. 2013
  15. [Gadermayr13a   ] Problems in Distortion Corrected Texture Classification and the Impact of Scale and Interpolation Michael Gadermayr, Michael Liedlgruber, Andreas Uhl, Andreas Vécsei In Proceedings of the 9th International Conference on Image Analysis and Processing (ICIAP'13), pp. 513-522, Springer LNCS, 8156, Sep. 2013
  16. [Gadermayr13b  ] Distortion Adaptive Image Classification - an Alternative to Barrel-Type Distortion Correction Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of the 9th International Symposium on Visual Computing (ISVC'13), pp. 465-474, Springer LNCS, 8034, July 2013
  17. [Gadermayr13c  ] Barrel-Type Distortion Compensated Fourier Feature Extraction Michael Gadermayr, Andreas Uhl, Andreas Vécsei In Proceedings of the 9th International Symposium on Visual Computing (ISVC'13), pp. 50-59, Springer LNCS, 8033, July 2013
  18. [Hegenbart13b ] On the Effects of De-Interlacing on the Classification Accuracy of Interlaced Endoscopic Videos with Indication for Celiac Disease Sebastian Hegenbart, Andreas Vécsei, Andreas Uhl, Georg Wimmer In Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems (CBMS'13)June 2013
  19. [Gschwandtner12a ] Improved Endoscope Distortion Correction does not Necessarily Enhance Mucosa-Classification based Medical Decision Support Systems Michael Gschwandtner, Jutta Hämmerle-Uhl, Yvonne Höller, Michael Liedlgruber, Andreas Uhl, Andreas Vécsei In Proceedings of the IEEE International Workshop on Multimedia Signal Processing (MMSP'12), pp. 158-163, Sep. 2012
  20. [Haemmerle12d ] Endoscope distortion correction does not (easily) improve mocusa-based classification of celiac disease Jutta Hämmerle-Uhl, Yvonne Höller, Andreas Uhl, Andreas Vécsei In Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2012, pp. 574-581, Springer Lecture Notes in Computer Science, 7512, Sep. 2012