Functional template-based SAR image segmentation

We present an approach to automatic image segmentation, in which user selected sets of examples and counter-examples supply information about the specific segmentation problem. In our approach, image segmentation is guided by a genetic algorithm which learns the appropriate subset and spatial combination of a collection of discriminating functions, associated with image features. The genetic algorithm encodes discriminating functions into a functional template representation, which can be applied to the input image to produce a candidate segmentation. The performance of each candidate segmentation is evaluated within the genetic algorithm, by a comparison to two physics-based techniques for region growing and edge detection. Through the process of segmentation, evaluation, and recombination, the genetic algorithm optimizes functional template design efficiently. Results are presented on real synthetic aperture radar (SAR) imagery of varying complexity.

[1]  S. Quegan,et al.  Understanding Synthetic Aperture Radar Images , 1998 .

[2]  Leen-Kiat Soh,et al.  Automated Sea Ice Segmentation (ASIS) , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[3]  R.P.H.M. Schoenmakers,et al.  Results of a hybrid segmentation method , 1994, Remote Sensing.

[4]  P.B.G. Dammert,et al.  Fuzzy c-means clustering algorithm for classification of sea ice and land cover from SAR images , 1997, Remote Sensing.

[5]  Nawapak Eua-anant,et al.  Genetic algorithm approach to image segmentation using morphological operations , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[6]  B. Solaiman,et al.  SIR-C polarimetric image segmentation by neural network , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.

[7]  Tamás Szirányi,et al.  Texture Classification and Segmentation by Cellular Neural Networks Using Genetic Learning , 1998, Comput. Vis. Image Underst..

[8]  Kun-Shan Chen,et al.  Remote sensing image segmentation using a Kalman filter-trained neural network , 1996, Int. J. Imaging Syst. Technol..

[9]  Hang Joon Kim,et al.  Automatic recognition of a car license plate using color image processing , 1994, Proceedings of 1st International Conference on Image Processing.

[10]  Leen-Kiat Soh,et al.  Segmentation of satellite imagery of natural scenes using data mining , 1999, IEEE Trans. Geosci. Remote. Sens..

[11]  Songde Ma,et al.  Unsupervised segmentation of SAR images , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[12]  S. Nayar,et al.  Early Visual Learning , 1996 .

[13]  Kun-Shan Chen,et al.  Remote sensing image segmentation using a Kalman filter‐trained neural network , 1996 .

[14]  Philippe Andrey,et al.  Selectionist relaxation: genetic algorithms applied to image segmentation , 1999, Image Vis. Comput..

[15]  Hyun Seung Yang,et al.  Robust image segmentation using genetic algorithm with a fuzzy measure , 1996, Pattern Recognit..

[16]  Stephen Grossberg,et al.  A neural network for enhancing boundaries and surfaces in synthetic aperture radar images , 1999, Neural Networks.

[17]  André Aurengo,et al.  Evolving descriptors for texture segmentation , 1997, Pattern Recognit..

[18]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[19]  Yukio Kosugi,et al.  Feature selection by genetic algorithm for MRI segmentation , 1999, Systems and Computers in Japan.

[20]  Riccardo Poli,et al.  Genetic algorithm-based interactive segmentation of 3D medical images , 1999, Image Vis. Comput..

[21]  A. J. Katz,et al.  Generating Image Filters for Target Recognition by Genetic Learning , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Barry T. Thomas,et al.  Automatic Selection of Gabor Filters for Pixel Classification , 1997 .

[23]  T. Stein.  International Geoscience And Remote Sensing Symposium , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[24]  P. Zingaretti,et al.  On Increasing the Objectiveness of Segmentation Results , 1999 .

[25]  Kenneth J. Hintz,et al.  Evolution of convolution kernels for feature extraction , 1995, Defense, Security, and Sensing.

[26]  Sanjeev R. Kulkarni,et al.  Learning Pattern Classification - A Survey , 1998, IEEE Trans. Inf. Theory.

[27]  F. Parmiggiani,et al.  Segmentation of SAR images by means of Gabor filters working at different spatial resolution , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.

[28]  Jacques Verly,et al.  Automatic Target Recognition for LADAR Imagery Using Functional Templates Derived From 3-D CAD Models , 1997 .

[29]  C. Sidney Burrus,et al.  Wavelet-based SAR speckle reduction and image compression , 1995, Defense, Security, and Sensing.

[30]  Jacques Verly,et al.  Machine Intelligent Automatic Recognition of Critical Mobile Targets in Laser Radar Imagery , 1993 .

[31]  Richard L. Delanoy.  Toolkit for image mining: user-trainable search tools , 1995 .

[32]  Robert Klepko,et al.  Hierarchical classifier design for airborne SAR images of ships , 1998, Defense, Security, and Sensing.

[33]  Kostas Delibasis,et al.  Designing texture filters with genetic algorithms: An application to medical images , 1997, Signal Process..