Skip to main content

Performance Evaluation of Super-Resolution Reconstruction Methods on Real-World Data

Abstract

The performance of a super-resolution (SR) reconstruction method on real-world data is not easy to measure, especially as a ground-truth (GT) is often not available. In this paper, a quantitative performance measure is used, based on triangle orientation discrimination (TOD). The TOD measure, simulating a real-observer task, is capable of determining the performance of a specific SR reconstruction method under varying conditions of the input data. It is shown that the performance of an SR reconstruction method on real-world data can be predicted accurately by measuring its performance on simulated data. This prediction of the performance on real-world data enables the optimization of the complete chain of a vision system; from camera setup and SR reconstruction up to image detection/recognition/identification. Furthermore, different SR reconstruction methods are compared to show that the TOD method is a useful tool to select a specific SR reconstruction method according to the imaging conditions (camera's fill-factor, optical point-spread-function (PSF), signal-to-noise ratio (SNR)).

References

  1. 1.

    Park SC, Park MK, Kang MG: Super-resolution image reconstruction: a technical overview. IEEE Signal Processing Magazine 2003,20(3):21–36. 10.1109/MSP.2003.1203207

    Article  Google Scholar 

  2. 2.

    Farsiu S, Robinson MD, Elad M, Milanfar P: Advances and challenges in super-resolution. International Journal of Imaging Systems and Technology 2004,14(2):47-57. 10.1002/ima.20007

    Article  Google Scholar 

  3. 3.

    Baker S, Kanade T: Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence 2002,24(9):1167-1183. 10.1109/TPAMI.2002.1033210

    Article  Google Scholar 

  4. 4.

    Lin Z, Shum H-Y: Fundamental limits of reconstruction-based superresolution algorithms under local translation. IEEE Transactions on Pattern Analysis and Machine Intelligence 2004,26(1):83-97. 10.1109/TPAMI.2004.1261081

    Article  Google Scholar 

  5. 5.

    Robinson MD, Milanfar P: Statistical performance analysis of super-resolution. IEEE Transactions on Image Processing 2006,15(6):1413-1428.

    Article  Google Scholar 

  6. 6.

    Bijl P, Valeton JM: Triangle orientation discrimination: the alternative to minimum resolvable temperature difference and minimum resolvable contrast. Optical Engineering 1998,37(7):1976-1983. 10.1117/1.601904

    Article  Google Scholar 

  7. 7.

    Bijl P, Schutte K, Hogervorst MA: Applicability of TOD, MTDP, MRT and DMRT for dynamic image enhancement techniques. Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XVII, April 2006, Kissimmee, Fla, USA, Proceedings of SPIE 6207: 1–12.

    Google Scholar 

  8. 8.

    Pham TQ, Bezuijen M, van Vliet LJ, Schutte K, Luengo Hendriks CL: Performance of optimal registration estimators. Visual Information Processing XIV, March 2005, Orlando, Fla, USA, Proceedings of SPIE 5817: 133–144.

    Article  Google Scholar 

  9. 9.

    Lucas BD, Kanade T: An iterative image registration technique with an application to stereo vision. Proceedings of the DARPA Image Understanding Workshop, April 1981, Washington, DC, USA 121–130.

    Google Scholar 

  10. 10.

    Kay SM: Fundamentals of Statistical Signal Processing: Estimation Theory. Prentice-Hall, Upper Saddle River, NJ, USA; 1993.

    Google Scholar 

  11. 11.

    Elad M, Hel-Or Y: A fast super-resolution reconstruction algorithm for pure translational motion and common space-invariant blur. IEEE Transactions on Image Processing 2001,10(8):1187-1193. 10.1109/83.935034

    Article  Google Scholar 

  12. 12.

    Lertrattanapanich S, Bose NK: High resolution image formation from low resolution frames using Delaunay triangulation. IEEE Transactions on Image Processing 2002,11(12):1427-1441. 10.1109/TIP.2002.806234

    MathSciNet  Article  Google Scholar 

  13. 13.

    Kaltenbacher E, Hardie RC: High resolution infrared image reconstruction using multiple, low resolution, aliased frames. Proceedings of IEEE National Aerospace and Electronics Conference (NAECON '96), May 1996, Dayton, Ky, USA 2: 702–709.

    Google Scholar 

  14. 14.

    Hardie RC, Barnard KJ, Bognar JG, Armstrong EE, Watson EA: High-resolution image reconstruction from a sequence of rotated and translated frames and its application to an infrared imaging system. Optical Engineering 1998,37(1):247-260. 10.1117/1.601623

    Article  Google Scholar 

  15. 15.

    Farsiu S, Robinson MD, Elad M, Milanfar P: Fast and robust multiframe super resolution. IEEE Transactions on Image Processing 2004,13(10):1327-1344. 10.1109/TIP.2004.834669

    Article  Google Scholar 

  16. 16.

    Pham TQ, van Vliet LJ, Schutte K: Robust fusion of irregularly sampled data using adaptive normalized convolution. EURASIP Journal on Applied Signal Processing 2006, 2006: 12 pages.

    Google Scholar 

  17. 17.

    Knutsson H, Westin C-F: Normalized and differential convolution. Proceedings of IEEE Society Conference on Computer Vision and Pattern Recognition (CVPR '93), June 1993, New York, NY, USA 515–523.

    Google Scholar 

  18. 18.

    Haralick RM, Watson L: A facet model for image data. Computer Graphics and Image Processing 1981,15(2):113-129. 10.1016/0146-664X(81)90073-3

    Article  Google Scholar 

  19. 19.

    Johnson J: Analysis of image forming systems. Proceedings of Image Intensifier Symposium, October 1958, Fort Belvoir, Va, USA 249–273.

    Google Scholar 

  20. 20.

    Valeton JM, Bijl P, Agterhuis E, Kriekaard S: T-CAT, a new thermal camera acuity tester. Infrared Imaging Systems: Design, Analysis, Modelling, and Testing XI, April 2000, Orlando, Fla, USA, Proceedings of SPIE 4030: 232–238.

    Google Scholar 

  21. 21.

    van Vliet LJ, Verbeek PW: Better geometric measurements based on photometric information. Proceedings of IEEE Instrumentation and Measurement Technology Conference (IMTC '94), May 1994, Hamamatsu, Japan 3: 1357–1360.

    Article  Google Scholar 

  22. 22.

    Pham TQ: Spatiotonal adaptivity in super-resolution of under-sampled image sequences, Ph.D. thesis. Quantitative Imaging Group, TU Delft, Delft, The Netherlands; 2006.

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to AWM van Eekeren.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (https://doi.org/creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

van Eekeren, A., Schutte, K., Oudegeest, O. et al. Performance Evaluation of Super-Resolution Reconstruction Methods on Real-World Data. EURASIP J. Adv. Signal Process. 2007, 043953 (2007). https://doi.org/10.1155/2007/43953

Download citation

Keywords

  • Information Technology
  • Input Data
  • Performance Evaluation
  • Vision System
  • Simulated Data