Paper Presentation & Seminar Topics: SAR Image Regularization With Fast Approximate Discrete Minimization

SAR Image Regularization With Fast Approximate Discrete Minimization


Synthetic aperture radar (SAR) images, like other coherent imaging modalities, suffer from speckle noise. The presence of this noise makes the automatic interpretation of images a challenging task and noise reduction is often a prerequisite for successful use of classical image processing algorithms. Numerous approaches have been proposed to filter speckle noise. Markov random field (MRF) modelization provides a convenient way to express both data fidelity constraints and desirable properties of the filtered image. In this context, total variation minimization has been extensively used to constrain the oscillations in the regularized image while preserving its edges. Speckle noise follows heavy-tailed distributions, and the MRF formulation leads to a minimization problem involving nonconvex log-likelihood terms. Such a minimization can be performed efficiently by computing minimum cuts on weighted graphs. Due to memory constraints, exact minimization, although theoretically possible, is not achievable on large images required by remote sensing applications. The computational burden of the state-of-the-art algorithm for approximate minimization (namely the -expansion) is too heavy specially when considering joint regularization of several images. We show that a satisfying solution can be reached, in few iterations, by performing a graph-cut-based combinatorial exploration of large trial moves. This algorithm is applied to joint regularization of the amplitude and interferometric phase in urban area SAR images.
Existing System:-

• SAR images are difficult to interpret not only with automatic image processing tools but also by human interpreters. This is mainly due to two specificities of the SAR system: first, SAR is coherent imagery and, therefore, subject to the speckle phenomenon; secondly, due to the microwave propagation, images are distance sampled leading to strong geometrical distortions.

Proposed System:-

• The regularized images obtained both on synthetic and real data were satisfying. The algorithm is faster than existing graphcut- based techniques. We have shown that joint regularization can be performed with little computation overload. It helps preventing loss of small objects (over-regularization) by merging all information.

Hardware Requirements:
• Processor : Pentium Iv 2.6 Ghz
• Ram : 512 Mb Dd Ram
• Monitor : 15” Color
• Hard Disk : 20 Gb

Software Requirements:
• Front End : Java, Swing
• Operating System : Window’s