Improved Segmentation of Speckled Images Using an Arithmetic-to-Geometric Mean Ratio Kernel

In this work, we improve a previously developed segmentation scheme aimed at extracting edge information from speckled images using a maximum likelihood edge detector. The scheme was based on finding a threshold for the probability density function of a new kernel defined as the arithmetic mean-to-geometric mean ratio field over a circular neighborhood set and, in a general context, is founded on a likelihood random field model (LRFM). The segmentation algorithm was applied to discriminated speckle areas obtained using simple elliptic discriminant functions based on measures of the signal-to-noise ratio with fractional order moments. A rigorous stochastic analysis was used to derive an exact expression for the cumulative density function of the probability density function of the random field. Based on this, an accurate probability of error was derived and the performance of the scheme was analysed. The improved segmentation scheme performed well for both simulated and real images and showed superior results to those previously obtained using the original LRFM scheme and standard edge detection methods. In particular, the false alarm probability was markedly lower than that of the original LRFM method with oversegmentation artifacts virtually eliminated. The importance of this work lies in the development of a stochastic-based segmentation, allowing an accurate quantification of the probability of false detection. Non visual quantification and misclassification in medical ultrasound speckled images is relatively new and is of interest to clinicians.

Authors:

• J. Daba
• J. Dubois

Keywords:

• Discriminant function
• false alarm
• segmentation
• signal-to-noise ratio
• skewness
• speckle.

References:

[1] A. Bovik, D. Munson, "Optimal Detection of Object Boundaries in
Uncorrelated Speckle," Optical Engineering, Vol. 25, No. 11, Nov.
1986.
[2] A. Bovik, "On Detecting Edges in Speckle Imagery," IEEE Transactions
on Acoustics Speech and Signal Processing, Vol. 36, No. 10, Oct. 1988.
[3] H. Arsenault, "Information Extraction from Images Degraded by
Speckle," Proceedings of IGARSS 87 Symposium, 1987, pp. 1317-1322.
[4] P. Kelly, H. Derin, "Adaptive Segmentation of Speckled Images Using a
Hierarchical RFM," IEEE Transactions on Acoustics, Speech, and
Signal Processing, Vol. 36, No. 10, Oct. 88.
[5] J. S. Daba and M. R. Bell, "Segmentation of Speckled Images Using a
Likelihood Random Field Model," Optical Engineering, accepted, to
appear in 2007.
[6] J. Goodman, "Statistical Properties of Laser Speckle Patterns," Speckle
and Related Phenomena, 2nd Edition, J. C. Dainty Ed., Springer Verlag,
NY, 1984.
[7] V. Frost and K. Shanmugan, "The Information Content of SAR Images
of Terrain," IEEE Transactions on Aerospace Electron. Syst., Vol. AES-
19, No. 5, pp. 768-774, 1993.
[8] V. Dutt and J. F. Greenleaf, "Speckle Analysis Using Signal to Noise
Ratios Based on Fractional Order Moments," Ultrasonic Imaging, Vol.
17, pp. 251-268, 1995.
[9] R. W. Prager, A. H. Gee, G. M. Treece, and L. Berman, "Speckle
Detection in Ultrasound Images Using First Order Statistics," Technical
Report CUED/F-INFENG/TR 415, University of Cambridge, Dept. of
Engineering, July 2001.