Local adaptive contrast enchancement in digital images

ABSTRACT

In this paper an algorithm for optical quality enhancement in low contrast images is proposed. The brightness dynamic region is increased using a non-linear transformation function, which is adapted from the local contrast. In a new approach, the local contrast is defined in every central pixel, using a four direction masking method and a statistical estimation of the local contrast value. Two adaptive thresholds locate the exact pixel positions where the proposed contrast adjustment algorithm is used to improve the image quality. In the evaluation process, several artificially distorted images are enhanced and the mean square error and peak noise ratio between the restored and the original images are estimated. The experimental results show both objective and subjective improvements in the image quality.

REFERENCES

• 1: J. R. Jenson, "Introductory digital image processing", Prentice Hall 2005
• 2: Jain, A. K., 1989, "Fundamentals of digital image processing, Prentice-Hall, Eglewood Cliffs NJ
• 3: Rosenfeld, A., and Kalk, A. C., 1982, "Digital Picture Processing", Prentice Hall, Academic Press, San Diego
• 4: J. DiCarlo and B. Wandell, "Rendering high dynamic range images," in Proc. SPIE Electronic Imaging, vol. 3965, (San Jose, CA), pp. 392--401, 2000.
• 5: Pfizer S. M. et al, "Adaptive Histogram Equalization and its Variations", Computer Vision, Graphics and Image Processing, vol. 39, pp. 355--368, 1987.
• 6: J. A. Stark and W. J. Fitzgerald, "An Alternative Algorithm for Adaptive Histogram Equalization", Graphical Models and Image Processing, vol.56, pp.180--185, 1996.
• 7: J. A. Stark, "Adaptive image contrast enhancement using generalizations of histogram equalization," IEEE Transactions on Image Processing, vol. 9, no. 5, pp. 889--896, 2000.
• 8: F. P. P. De Vries "Automatic, adaptive, brightness independent contrast enhancement", Signal Processing vol. 21, pp. 169--182, 1990.
• 9: J. L. Starck, F. Murtagh, E. Candes, and D. L. Donoho, "Gray and color image contrast enhancement by the curvelet transform," IEEE Trans. Im. Proc., vol. 12, pp. 706--717, 2003.
• 10: N. Bonnier and E. P. Simoncelli, "Locally Adaptive Multiscale Contrast Optimization", Proc. 12th IEEE Intl. Conf. Image Processing Vol I, pp 949--952, Sep 2005.
• 11: Seul M., O'Gorman L. and Sammon M., "Practical Algorithms for Image Analysis", Cambridge University Press, 2001
• 12: Hampel F., Ronchetti E., Rousseevw R., Stahel W. "Robust Statistics: An Approach Based on Influence Functions", J. Wiley, 1986
• 13: Tukey J. W., "Exploratory Data Analysis", Addison - Wesley, Reading MA, 1971
• 14: Acre G. R and Mcloughlim M. P. "Theoretical analysis of the max/median filter", IEEE Trans. on Acoustics, Speech and Signal Processing, Vol. 35, No. 1, 1987
• 15: J. Hertz, R. Plamer, "Introduction to the neural computation", Addison Wesley, California, 1991
• 16: Kramer H. and Bruchner J. "Iteration of a non-linear transformation for the enhancement of digital images", IEEE Trans. On Systems, Man and Cybernetics, Vol.7, pp.53--58, 1975
• 17: Serra J. "Image Analysis and Mathematical Morphology", Academic Press, 1982
• 18: Gongalez R. and Woods R., "Digital Image Processing", Addison - Wesley Publishing Co, 1993
• 19: Beghdadi, A., and Negrate, A. L., 1989, "Contrast enhancement technique based on local detection of edges", Computer Vision, Graphics and Image Processing, 46, 162--174.
• 20: Korpi-Anttila, "Automatic color enhancement and scene change detection of digital video", Licentiate thesis, Helsinki University of Technology, Laboratory of Media Technology, 2003.
• 21: D. L. Ruderman, "The statistics of natural images," Network: Computation in Neural Systems, vol. 5, pp. 517--548, 1996.

INDEX TERMS

Keywords:
brightnesses, contrast, digital image, dynamic region, image enhancement, pixel, transformation function