Hyperspectral image segmentation through evolved cellular automata

Segmenting multidimensional images, in particular hyperspectral images, is still an open subject. Two are the most important issues in this field. On one hand, most methods do not preserve the multidimensional character of the signals throughout the segmentation process. They usually perform an early projection of the hyperspectral information to a two dimensional representation with the consequent loss of the large amount of spectral information these images provide. On the other hand, there is usually very little and dubious ground truth available, making it very hard to train and tune appropriate segmentation and classification strategies. This paper describes an approach to the problem of segmenting and classifying regions in multidimensional images that performs a joint two-step process. The first step is based on the application of cellular automata (CA) and their emergent behavior over the hyperspectral cube in order to produce homogeneous regions. The second step employs a more traditional SVM in order to provide labels for these regions to classify them. The use of cellular automata for segmentation in hyperspectral images is not new, but most approaches to this problem involve hand designing the rules for the automata and, in general, average out the spectral information present. The main contribution of this paper is the study of the application of evolutionary methods to produce the CA rule sets that result in the best possible segmentation properties under different circumstances without resorting to any form of projection until the information is presented to the user. In addition, we show that the evolution process we propose to obtain the rules can be carried out over RGB images and then the resulting automata can be used to process multidimensional hyperspectral images successfully, thus avoiding the problem of lack of appropriately labeled ground truth images. The procedure has been tested over synthetic and real hyperspectral images and the results are very competitive.

[1]  Guy Flouzat,et al.  Spatial and spectral segmentation of satellite remote sensing imagery using processing graphs by mathematical morphology , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[2]  Wolfgang Reinhardt,et al.  Image segmentation for the purpose of object-based classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[3]  Manuel Graña,et al.  Two lattice computing approaches for the unsupervised segmentation of hyperspectral images , 2009, Neurocomputing.

[4]  Jon Atli Benediktsson,et al.  A new approach for the morphological segmentation of high-resolution satellite imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[5]  J. Schwartz,et al.  Theory of Self-Reproducing Automata , 1967 .

[6]  Jean-Michel Roger,et al.  Hyperspectral image segmentation: The butterfly approach , 2009, 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[7]  Richard J. Duro,et al.  Using Gaussian Synapse ANNs for Hyperspectral Image Segmentation and Endmember Extraction , 2008 .

[8]  Albert Y. Zomaya,et al.  Evolving Cellular Automata for Location Management in Mobile Computing Networks , 2003, IEEE Trans. Parallel Distributed Syst..

[9]  Tiziana Veracini,et al.  Robust hyperspectral image segmentation based on a non-Gaussian model , 2010, 2010 2nd International Workshop on Cognitive Information Processing.

[10]  Richard J. Duro,et al.  Towards real-time hyperspectral image processing, a GP-GPU implementation of target identification , 2011, Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems.

[11]  Peijun Li,et al.  Evaluation of multiscale morphological segmentation of multispectral imagery for land cover classification , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[12]  P. P. Chaudhuri,et al.  A Survey on Cellular Automata ∗ , 2003 .

[13]  J. Tilton,et al.  Analysis of hierarchically related image segmentations , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[14]  Alvy Ray Smith,et al.  Introduction to and Survey of Cellular Automata or Polyautomata Theory1 , 2001 .

[15]  Claude Kauffmann,et al.  Seeded ND medical image segmentation by cellular automaton on GPU , 2010, International Journal of Computer Assisted Radiology and Surgery.

[16]  Matthew A. Lee,et al.  Applying cellular automata to hyperspectral edge detection , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[17]  Romà Tauler,et al.  Spectroscopic imaging and chemometrics: a powerful combination for global and local sample analysis , 2004 .

[18]  Aly A. Farag,et al.  A unified framework for MAP estimation in remote sensing image segmentation , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[19]  X. Jia,et al.  A Cellular Automata approach for superpixel segmentation , 2011, 2011 4th International Congress on Image and Signal Processing.

[20]  Bruce J. Tromberg,et al.  Hyperspectral face recognition for homeland security , 2003, SPIE Defense + Commercial Sensing.

[21]  Wilfried Elmenreich,et al.  Evolving Self-organizing Cellular Automata Based on Neural Network Genotypes , 2011, IWSOS.

[22]  Manuel Graña,et al.  A morphological cellular automata based on morphological independence , 2012, Log. J. IGPL.

[23]  Jon Atli Benediktsson,et al.  Recent Advances in Techniques for Hyperspectral Image Processing , 2009 .

[24]  James P. Crutchfield,et al.  Revisiting the Edge of Chaos: Evolving Cellular Automata to Perform Computations , 1993, Complex Syst..

[25]  Jean-Yves Tourneret,et al.  Markov random fields for joint unmixing and segmentation of hyperspectral images , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[26]  David L. Glackin,et al.  Civil, Commercial, and International Remote Sensing Systems and Geoprocessing , 1999 .

[27]  J.L. Crespo,et al.  Unmixing low ratio endmembers through Gaussian synapse ANNs in hyperspectral images , 2004, 2004 IEEE International Conference onComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA..

[28]  Pablo Quesada-Barriuso,et al.  Efficient segmentation of hyperspectral images on commodity GPUs , 2012, KES.

[29]  Ayan Chakrabarti,et al.  Statistics of real-world hyperspectral images , 2011, CVPR 2011.

[30]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[31]  Jon Atli Benediktsson,et al.  Segmentation and classification of hyperspectral images using watershed transformation , 2010, Pattern Recognit..

[32]  Antonio J. Plaza,et al.  Hyperspectral Image Segmentation Using a New Bayesian Approach With Active Learning , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Liming Zhang,et al.  An approach based on self-organizing map and fuzzy membership for decomposition of mixed pixels in hyperspectral imagery , 2010, Pattern Recognit. Lett..

[34]  David A. Landgrebe,et al.  Hyperspectral image data analysis , 2002, IEEE Signal Process. Mag..

[35]  Zhang Chuanwu.  Performance Analysis of the CPLD/FPGA Implementation of Cellular Automata , 2008, 2008 International Conference on Embedded Software and Systems Symposia.