A hierarchical Markovian model for multiscale region-based classification of vector-valued images

We propose a new classification method for vector-valued images, based on: 1) a causal Markovian model, defined on the hierarchy of a multiscale region adjacency tree (MRAT), and 2) a set of nonparametric dissimilarity measures that express the data likelihoods. The image classification is treated as a hierarchical labeling of the MRAT, using a finite set of interpretation labels (e.g., land cover classes). This is accomplished via a noniterative estimation of the modes of posterior marginals (MPM), inspired from existing approaches for Bayesian inference on the quadtree. The paper describes the main principles of our method and illustrates classification results on a set of artificial and remote sensing images, together with qualitative and quantitative comparisons with a variety of pixel-based techniques that follow the Bayesian-Markovian framework either on hierarchical structures or the original image lattice.

[1]  Azriel Rosenfeld,et al.  A critical view of pyramid segmentation algorithms , 1990, Pattern Recognit. Lett..

[2]  Joachim M. Buhmann,et al.  Unsupervised Texture Segmentation in a Deterministic Annealing Framework , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[4]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[5]  Bernard A. Engel,et al.  Analysis of classification results of remotely sensed data and evaluation of classification algorithms , 1995 .

[6]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[7]  Josiane Zerubia,et al.  A Hierarchical Markov Random Field Model and Multitemperature Annealing for Parallel Image Classification , 1996, CVGIP Graph. Model. Image Process..

[8]  Sebastiano B. Serpico,et al.  Partially supervised classification of remote sensing images using SVM-based probability density estimation , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[9]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[10]  Andrew P. Witkin,et al.  Scale-space filtering: A new approach to multi-scale description , 1984, ICASSP.

[11]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[12]  Fernand Meyer,et al.  Hierarchies of Partitions and Morphological Segmentation , 2001, Scale-Space.

[13]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Charles A. Bouman,et al.  A multiscale random field model for Bayesian image segmentation , 1994, IEEE Trans. Image Process..

[15]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Gabriele Moser,et al.  Partially Supervised classification of remote sensing images through SVM-based probability density estimation , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Patrick Pérez,et al.  Color-Based Probabilistic Tracking , 2002, ECCV.

[18]  Wenyuan Xu,et al.  Analysis and design of anisotropic diffusion for image processing , 1994, Proceedings of 1st International Conference on Image Processing.

[19]  Patrick Pérez,et al.  Sonar image segmentation using an unsupervised hierarchical MRF model , 2000, IEEE Trans. Image Process..

[20]  Patrick Pérez,et al.  Discrete Markov image modeling and inference on the quadtree , 2000, IEEE Trans. Image Process..

[21]  I. Vanhamel,et al.  A hierarchical Markovian model for multiscale region-based classification of multispectral images , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[22]  Donald Geman,et al.  Boundary Detection by Constrained Optimization , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Farid Melgani,et al.  An explicit fuzzy supervised classification method for multispectral remote sensing images , 2000, IEEE Trans. Geosci. Remote. Sens..

[24]  Patrick Pérez,et al.  Hierarchical Markovian segmentation of multispectral images for the reconstruction of water depth maps , 2004, Comput. Vis. Image Underst..

[25]  Michael Kerckhove,et al.  Scale-Space and Morphology in Computer Vision , 2001, Lecture Notes in Computer Science 2106.

[26]  Qiong Jackson,et al.  Adaptive Bayesian contextual classification based on Markov random fields , 2002, IEEE Trans. Geosci. Remote. Sens..

[27]  Hichem Sahli,et al.  Hierarchical segmentation via a diffusion scheme in color/texture feature space , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

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

[29]  Silvano Di Zenzo,et al.  A note on the gradient of a multi-image , 1986, Comput. Vis. Graph. Image Process..

[30]  Hichem Sahli,et al.  Multiscale gradient watersheds of color images , 2003, IEEE Trans. Image Process..

[31]  Patrick Pérez,et al.  Semi-iterative inference with hierarchical models , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[32]  O. F. Olsen.  Multi-Scale Segmentation of Grey-Scale Images , 1996 .

[33]  Vikash Kumar,et al.  A MRF model-based segmentation approach to classification for multispectral imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[34]  Guillermo Sapiro,et al.  Robust anisotropic diffusion , 1998, IEEE Trans. Image Process..

[35]  P. Lions,et al.  Image selective smoothing and edge detection by nonlinear diffusion. II , 1992 .

[36]  Sebastiano B. Serpico,et al.  Neural networks for classification of remotely sensed images , 1996 .

[37]  Joachim M. Buhmann,et al.  Empirical evaluation of dissimilarity measures for color and texture , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[38]  Qiong Jackson,et al.  Adaptive Bayesian contextual classification based on Markov random fields , 2002, IEEE International Geoscience and Remote Sensing Symposium.