Skip to main content
SpringerLink
Log in

Novel multi-scale retinex with color restoration on graphics processing unit

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

The multi-scale retinex with color restoration (MSRCR) was developed as a general-purpose image enhancement algorithm that provides simultaneous dynamic range compression, local lightness/contrast enhancement, and good color rendition, and has been successfully used for a wide variety of imagery from diverse fields. While the MSRCR performs good enhancement in most images, the output image can sometimes be further visually optimized during our experiments. An improved MSRCR+Autolevels (AL) algorithm is presented, which can eliminate the impact of a small number of outliers in the histogram of the image and further improve the contrast of an image. New extension significantly improves the visual performance of the MSRCR algorithm. However, the MSRCR+AL containing a large number of complex calculations is computationally expensive, limiting real-time applications. In this paper, a parallel application of the MSRCR+AL algorithm on a graphics processing unit (GPU) is presented. For the various configurations in our test, the GPU-accelerated MSRCR+AL shows a scalable speedup as the resolution of an image increases. The up to 45× speedup (1,024 × 1,024) over the single-threaded CPU counterpart shows a promising direction of using the GPU-based MSRCR+AL in large-scale, time-critical applications. We also achieved 17 frames per second in video processing (1,280 × 720).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Archirapatkave, V., Sumilo, H., See, S., Achalakul, T.: GPGPU acceleration algorithm for medical image reconstruction. In: Parallel and Distributed Processing with Applications (ISPA), 2011 IEEE 9th International Symposium on, IEEE, pp. 41–46 (2011)

  2. Clayton, T., Murray, A., Lindsay, I.: GP-GPU: bridging the gap between modelling & experimentation. In: Adaptive Hardware and Systems, 2009. AHS 2009. NASA/ESA Conference on, IEEE, pp. 453–459 (2009)

  3. Fechteler, P., Eisert, P.: Accelerated video encoding using render context information. In: Image Processing (ICIP), 2010 17th IEEE International Conference on, IEEE, pp. 2033–2036 (2010)

  4. Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Pearson Prentice Hall, Third ed. (2008)

  5. Hines, G., Rahman, Z., Jobson, D., Woodell, G.: DSP implementation of the retinex image enhancement algorithm. In: Visual Information Processing XIII, Proceedings of SPIE, vol. 5438 (2004)

  6. Hines, G., Rahman, Z., Jobson, D., Woodell, G.: Single-scale retinex using digital signal processors. In: Global Signal Processing Conference, Citeseer, vol. 27 (2004)

  7. Hines, G., Rahman, Z., Jobson, D., Woodell, G., Harrah, S.: Real-time enhanced vision system 5778 (2005)

  8. Hines, G., Rahman, Z., Jobson, D., Woodell, G.: Real-time enhancement, registration, and fusion for a multi-sensor enhanced vision system. Proc. SPIE 6226:622609 (2006)

    Article  Google Scholar 

  9. Huang, M., Wei, S., Huang, B., Chang, Y.: Accelerating the kalman filter on a gpu. In: Parallel and Distributed Systems (ICPADS), 2011 IEEE 17th International Conference on, IEEE, pp. 1016–1020 (2011)

  10. Jiang B, Rahman Z (2012) Runway hazard detection in poor visibility conditions. Proc. SPIE 8300:83000H

    Article  Google Scholar 

  11. Jinzhu, Y., Han, F., Chaolu, F., Dazhe, Z., Yanfei, W.: An accelerative method for multimodality medical image registration based on cuda. In: Image and Signal Processing (CISP), 2011 4th International Congress on, IEEE, vol. 4, pp. 1817–1821 (2011)

  12. Jobson, D., Rahman, Z., Woodell, G.: Retinex image processing: improved fidelity to direct visual observation (1996)

  13. Jobson, D., Rahman, Z., Woodell, G.: Properties and performance of a center/surround retinex. Image Proc. IEEE Trans. 6(3):451–462 (1997)

    Article  Google Scholar 

  14. Jobson, D., Rahman, Z., Woodell, G.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. Image Proc. IEEE Trans. 6(7):965–976 (1997)

    Article  Google Scholar 

  15. Jobson, D.; Rahman, Z.; Woodell, G.: The spatial aspect of color and scientific implications of retinex image processing. In: SPIE International Symposium on AeroSense, Proceedings of the Conference on Visual Information Processing X (2001)

  16. Jobson, D., Rahman, Z., Woodell, G.: Feature visibility limits in the non-linear enhancement of turbid images. Proc. SPIE 5108, (2003)

  17. Kinsner, M., Capson, D., Spence, A.: Scale-space ridge detection with gpu acceleration. In: Electrical and Computer Engineering, 2008. CCECE 2008. Canadian Conference on, IEEE, pp. 001, 527–001, 530 (2008)

  18. Kirk, D., Wen-mei, W., Hwu, W.: Programming massively parallel processors: a hands-on approach. Morgan Kaufmann (2010)

  19. van der Laan, W., Jalba, A., Roerdink, J.: Accelerating wavelet lifting on graphics hardware using cuda. IEEE Trans. Parallel Distrib. Syst. 22(1):132–146 (2011)

    Article  Google Scholar 

  20. Land E (1983) Recent advances in retinex theory and some implications for cortical computations: color vision and the natural image. Proc. Natl. Acad. Sci. USA 80(16):5163

    Article  Google Scholar 

  21. Land, E: An alternative technique for the computation of the designator in the retinex theory of color vision. Proc. Natl. Acad. Sci. 83(10):3078–3080 (1986)

    Article  Google Scholar 

  22. Land, E.: Recent advances in retinex theory. Vision Res. 26(1):7–21 (1986)

    Article  Google Scholar 

  23. Rahman, Z., Woodell, G., Jobson, D.: Retinex image enhancement: application to medical images. In: NASA Workshop on New Partnerships in Medical Diagnostic Imaging (2001)

  24. Rahman, Z., Jobson, D., Woodell, G., Hines, G. Multisensor fusion and enhancement using the retinex image enhancement algorithm. Proc. SPIE Visual Inform. Process. 4736:36–44 (2002)

    Google Scholar 

  25. Rahman, Z., Jobson, D., Woodell, G. Retinex processing for automatic image enhancement. J. Electron. Imaging 13:100–110 (2004)

    Article  Google Scholar 

  26. Sanders, J.; Kandrot, E.: CUDA by example: an introduction to general-purpose GPU programming. Addison-Wesley Professional (2010)

  27. Shen G, Gao G, Li S, Shum H, Zhang Y (2005) Accelerate video decoding with generic gpu. Circuits Syst. Video Technol. IEEE Trans. 15(5):685–693

    Article  Google Scholar 

  28. Shi, L., Chen, H., Sun, J., Li, K.: vCUDA: Gpu-accelerated high-performance computing in virtual machines. Comput. IEEE Trans. 61(6):804–816 (2012). doi:10.1109/TC.2011.112

    Article  MathSciNet  Google Scholar 

  29. Stockham Jr., T.G., Cannon, T.M., Robert, B.: Ingebretsen (1975) blind deconvolution through digital signal processing. Proc. IEEE 63.4 678–692 (1975)

  30. Sun, Y., Sun, X., Zhang, H.: Research on parallel cone-beam ct image reconstruction on cuda-enabled gpu. In: Image Processing (ICIP), 2010 17th IEEE International Conference on, IEEE, pp. 4501–4504 (2010)

  31. Tsai, S., Cheng, C., Li, C., Chen, L.: A real-time 1080p 2d-to-3d video conversion system. In: Consumer Electronics (ICCE), 2011 IEEE International Conference on, IEEE, pp. 803–804 (2011)

  32. Woodell, G., Rahman, Z., Jobson, D., Hines, G.: Enhanced images for checked and carry-on baggage and cargo screening. Proc. SPIE 5403:582 (2004)

    Article  Google Scholar 

  33. Woodell, G., Jobson, D., Rahman, Z., Hines, G. Enhancement of imagery in poor visibility conditions. Proc. SPIE 5778:673 (2005)

    Article  Google Scholar 

  34. Woodell, G., Jobson, D., Rahman, Z., Hines, G.: Advanced image processing of aerial imagery. Proc. SPIE 6246:62460E (2006)

    Article  Google Scholar 

  35. Wright, W.: The Measurement of Colour. London, Second ed. (1958)

  36. Zavala-Romero, O., Baese, A., Meyer-Baese, U.: Multiplatform gpgpu implementation of the active contours without edges algorithm. Proc. SPIE 8399:83990E (2012)

    Article  Google Scholar 

  37. Zhao, J., Zhou, H.: Design and optimization of remote sensing image fusion parallel algorithms based on cpu-gpu heterogeneous platforms. In: Image and Signal Processing (CISP), 2011 4th International Congress on, IEEE, vol. 3, pp. 1623–1627 (2011)

Download references

Acknowledgments

The authors wish to thank the NASA Aviation Safety Program, External Hazards Sensing and Mitigation for the funding which made this work possible. In particular, Dr. Jiang was funded by NASA Grant#NNL09AA00A to the National Institute of Aerospace.

Author information

Authors and Affiliations

  1. National Institute of Aerospace, 100 Exploration Way, Hampton, VA, 23666, USA

    Bo Jiang

  2. NASA Langley Research Center, Electromagnetics and Sensors Branch, 8 North Dryden Street Mail Stop 473, Hampton, VA, 23681, USA

    Glenn A. Woodell & Daniel J. Jobson

Authors
  1. Bo Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Glenn A. Woodell
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daniel J. Jobson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bo Jiang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Jiang, B., Woodell, G.A. & Jobson, D.J. Novel multi-scale retinex with color restoration on graphics processing unit. J Real-Time Image Proc 10, 239–253 (2015). https://doi.org/10.1007/s11554-014-0399-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-014-0399-9

Keywords

Search

Navigation