Removing Impulse Bursts from Images by Training-Based Filtering

The characteristics of impulse bursts in remote sensing images are analyzed and a model for this noise is proposed. The model also takes into consideration other noise types, for example, the multiplicative noise present in radar images. As a case study, soft morphological filters utilizing a training-based optimization scheme are used for the noise removal. Different approaches for the training are discussed. It is shown that these techniques can provide an effective removal of impulse bursts. At the same time, other noise types in images, for example, the multiplicative noise, can be suppressed without compromising good edge and detail preservation. Numerical simulation results, as well as examples of real remote sensing images, are presented.

[1]  Jong-Sen Lee,et al.  Speckle analysis and smoothing of synthetic aperture radar images , 1981 .

[2]  Jong-Sen Lee,et al.  Digital image smoothing and the sigma filter , 1983, Comput. Vis. Graph. Image Process..

[3]  Jaakko Astola,et al.  Soft morphological filtering , 1995, Journal of Mathematical Imaging and Vision.

[4]  R. Crinon.  The Wilcoxon filter: A robust filtering scheme , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Michael L. Lightstone,et al.  A new efficient approach for the removal of impulse noise from highly corrupted images , 1996, IEEE Trans. Image Process..

[6]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[7]  Vladimir V. Lukin,et al.  mm-band radar image filtering with texture information preservation , 2001, Fourth International Kharkov Symposium 'Physics and Engineering of Millimeter and Sub-Millimeter Waves'. Symposium Proceedings (Cat. No.01EX429).

[8]  Moncef Gabbouj,et al.  A training framework for stack and Boolean filtering-fast optimal design procedures and robustness case study , 1996, IEEE Trans. Image Process..

[9]  Nikolay N. Ponomarenko,et al.  Modified sigma filter for processing images corrupted by multiplicative and impulsive noise , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[10]  Edward J. Coyle,et al.  Adaptive stack filtering under the mean absolute error criterion , 1990, Other Conferences.

[11]  P. Kuosmanen,et al.  Breakdown points and optimal soft morphological filtering , 1996, 1996 IEEE Digital Signal Processing Workshop Proceedings.

[12]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[13]  Nikolay N. Ponomarenko,et al.  Two-stage radar image despeckling based on local statistic Lee and sigma filtering , 2001, IS&T/SPIE Electronic Imaging.

[14]  Jaakko Astola,et al.  Soft morphological filters: a robust morphological filtering method , 1994, J. Electronic Imaging.

[15]  J. Astola,et al.  Fundamentals of Nonlinear Digital Filtering , 1997 .

[16]  Ioannis Pitas,et al.  Nonlinear Digital Filters - Principles and Applications , 1990, The Springer International Series in Engineering and Computer Science.

[17]  Pauli Kuosmanen,et al.  Training-based optimization of soft morphological filters , 1996, J. Electronic Imaging.

[18]  David H. Eberly,et al.  The WMMR filters: a class of robust edge enhancers , 1993, IEEE Trans. Signal Process..

[19]  Alexander A. Zelensky,et al.  Neural network application for primary local recognition and nonlinear adaptive filtering of images , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).