KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Author: search.filters.author.Intajag, SathitSubject: search.filters.subject.SAR

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    SAR segmentation using anisotropic diffusion
    (2005-12-01)
    Intajag, Sathit
    ;
    Tipsuwanpon, Vittaya
    Speckle effects are commonly observed in a synthetic aperture radar (SAR) image, which applies in many land applications, such as agriculture or forestry. However, although the human eye is able to derive the meaningful information from the SAR image, automatic processing is very difficult to distinguish the objects in the images because of the noise effect present in the image. This paper presents a segmentation method of the SAR images, which uses an anisotropic diffusion algorithm with an inherence region-growing algorithm. Anisotropic diffusion is modified in logarithmic domain to remove the speckle noise and to identify the homogeneous regions in ERS and JERS satellite data. The modified diffusion method is formulated with a tensor technique, varying with both the location of a pixel in the image and the orientation of the local image geometry vicinity the pixels. In our algorithm, SAR images are transformed into logarithmic domain and using the modified anisotropic diffusion to grow the homogeneous regions in the noise environment; consequently, the segmented image in the logarithm domain is converted to the intensity domain by an exponential function. On the other hand, our diffusion algorithm can stop itself by a standard deviation to mean criteria. Simulation results on the satellite images are provided to indicate the effectiveness of the proposed method when used to remove the effects of speckle noise almost as well as that of the additive noise. The evaluation of the proposed method employs the theoretical gain in equivalent numbers of looks (ENL). © 2005 SICE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Speckle reduction using fuzzy morphological anisotropic diffusion
    (2005-12-01)
    Easanuruk, Somchai
    ;
    Mitatha, Somsak
    ;
    Intajag, Sathit
    ;
    Chitwong, Sakreya
    One of important tasks of radar image processing is reducing speckle noise as preprocessing to enhance preformance of other processing such as segmentation, classification, etc. In this paper, we then apply the fuzzy morphology together with anisotropic diffusion to reduce speckled noise of SAR image. Anisotropic diffusion is designed based on additive noise model, but the form of speckled image is in multiplicative speckle model. To transform additive noise model into multiplicative speckle model, logarithmic transformation is then used. Our algorithm performs in log-domain. Finally, despeckled image being in log-domain is converted into spatial domain by using exponential transformation. Simulated image as speckled image is performed with our algorithm to show and compare results with recent reports in term of both signal to noise ratio (SNR) and the equivalent number of looks (ENL). Also, real SAR image is performed to confirm results in term of ENL only. Results from our experiment are shown that de-speckled image can smooth out in homogeneous area and preserve edge in heterogeneous area. Both visual image and numerical results are used to show all results. © 2005 IEEE.