Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm
A valid unsupervised and multiscale segmentation of synthetic aperture radar(SAR) imagery is proposed by a combination GA-EM of the Expectation Maximization(EM) algorith with the genetic algorithm (GA). The mixture multiscale autoregressive(MMAR) model is introduced to characterize and exploit the s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2008-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/8/3/1704/ |
| _version_ | 1798041198410072064 |
|---|---|
| author | Ze-Tao Jiang Hua Zhang Xian-Bin Wen |
| author_facet | Ze-Tao Jiang Hua Zhang Xian-Bin Wen |
| author_sort | Ze-Tao Jiang |
| collection | DOAJ |
| description | A valid unsupervised and multiscale segmentation of synthetic aperture radar(SAR) imagery is proposed by a combination GA-EM of the Expectation Maximization(EM) algorith with the genetic algorithm (GA). The mixture multiscale autoregressive(MMAR) model is introduced to characterize and exploit the scale-to-scale statisticalvariations and statistical variations in the same scale in SAR imagery due to radar speckle,and a segmentation method is given by combining the GA algorithm with the EMalgorithm. This algorithm is capable of selecting the number of components of the modelusing the minimum description length (MDL) criterion. Our approach benefits from theproperties of the Genetic and the EM algorithm by combination of both into a singleprocedure. The population-based stochastic search of the genetic algorithm (GA) exploresthe search space more thoroughly than the EM method. Therefore, our algorithm enablesescaping from local optimal solutions since the algorithm becomes less sensitive to itsinitialization. Some experiment results are given based on our proposed approach, andcompared to that of the EM algorithms. The experiments on the SAR images show that theGA-EM outperforms the EM method. |
| first_indexed | 2024-04-11T22:19:00Z |
| format | Article |
| id | doaj.art-4c28e3b331f74a8f9738d09ccd1fff82 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:19:00Z |
| publishDate | 2008-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4c28e3b331f74a8f9738d09ccd1fff822022-12-22T04:00:17ZengMDPI AGSensors1424-82202008-03-018317041711Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic AlgorithmZe-Tao JiangHua ZhangXian-Bin WenA valid unsupervised and multiscale segmentation of synthetic aperture radar(SAR) imagery is proposed by a combination GA-EM of the Expectation Maximization(EM) algorith with the genetic algorithm (GA). The mixture multiscale autoregressive(MMAR) model is introduced to characterize and exploit the scale-to-scale statisticalvariations and statistical variations in the same scale in SAR imagery due to radar speckle,and a segmentation method is given by combining the GA algorithm with the EMalgorithm. This algorithm is capable of selecting the number of components of the modelusing the minimum description length (MDL) criterion. Our approach benefits from theproperties of the Genetic and the EM algorithm by combination of both into a singleprocedure. The population-based stochastic search of the genetic algorithm (GA) exploresthe search space more thoroughly than the EM method. Therefore, our algorithm enablesescaping from local optimal solutions since the algorithm becomes less sensitive to itsinitialization. Some experiment results are given based on our proposed approach, andcompared to that of the EM algorithms. The experiments on the SAR images show that theGA-EM outperforms the EM method.http://www.mdpi.com/1424-8220/8/3/1704/SAR ImageUnsupervised SegmentationMultiscaleGenetic Algorithms. |
| spellingShingle | Ze-Tao Jiang Hua Zhang Xian-Bin Wen Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm Sensors SAR Image Unsupervised Segmentation Multiscale Genetic Algorithms. |
| title | Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm |
| title_full | Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm |
| title_fullStr | Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm |
| title_full_unstemmed | Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm |
| title_short | Multiscale Unsupervised Segmentation of SAR Imagery Using the Genetic Algorithm |
| title_sort | multiscale unsupervised segmentation of sar imagery using the genetic algorithm |
| topic | SAR Image Unsupervised Segmentation Multiscale Genetic Algorithms. |
| url | http://www.mdpi.com/1424-8220/8/3/1704/ |
| work_keys_str_mv | AT zetaojiang multiscaleunsupervisedsegmentationofsarimageryusingthegeneticalgorithm AT huazhang multiscaleunsupervisedsegmentationofsarimageryusingthegeneticalgorithm AT xianbinwen multiscaleunsupervisedsegmentationofsarimageryusingthegeneticalgorithm |