Cluster validation for unsupervised stochastic model-based image segmentation

Image segmentation is an important processing stage in many image analysis problems. Often this must be done in an unsupervised fashion in that training data is not available. A major obstacle in such applications is the determination of the number of distinct regions present in an image. This problem, called the cluster validation problem, remains essentially unsolved. We investigate the cluster validation problem associated with the use of a previously developed unsupervised segmentation algorithm based upon the expectation-maximization (EM) algorithm. We consider several well-known information-theoretic criteria (ICs) as candidate solutions. We show that these criteria generally provide inappropriate results. As an alternative we propose a model-fitting technique in which the complete data log-likelihood functional is modeled as an exponential function in the number of classes acting, and the class estimate is related to the rise time. This new validation technique is shown to be robust and outperform the ICs in our experiments.<<ETX>>

[1]  T.F. Quatieri,et al.  Statistical model-based algorithms for image analysis , 1986, Proceedings of the IEEE.

[2]  David B. Cooper,et al.  Simple Parallel Hierarchical and Relaxation Algorithms for Segmenting Noncausal Markovian Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Hirotugu Akaike,et al.  On entropy maximization principle , 1977 .

[4]  Henry Stark,et al.  Probability, Random Processes, and Estimation Theory for Engineers , 1995 .

[5]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

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

[7]  D. Rubin,et al.  Estimation and Hypothesis Testing in Finite Mixture Models , 1985 .

[8]  Jun Zhang,et al.  Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentation , 1994, IEEE Trans. Image Process..

[9]  S. Sclove.  Application of model-selection criteria to some problems in multivariate analysis , 1987 .

[10]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[11]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[12]  A. F. Smith,et al.  Statistical analysis of finite mixture distributions , 1986 .

[13]  Sridhar Lakshmanan,et al.  Simultaneous Parameter Estimation and Segmentation of Gibbs Random Fields Using Simulated Annealing , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  James W. Modestino,et al.  Texture Discrimination Based Upon an Assumed Stochastic Texture Model , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Federico Girosi,et al.  Parallel and deterministic algorithms from MRFs: surface reconstruction and integration , 1990, ECCV.

[16]  Patrick A. Kelly,et al.  Adaptive segmentation of speckled images using a hierarchical random field model , 1988, IEEE Trans. Acoust. Speech Signal Process..

[17]  David B. Cooper,et al.  Bayesian Clustering for Unsupervised Estimation of Surface and Texture Models , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

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

[19]  R. J. Bhansali,et al.  A derivation of the information criteria for selecting autoregressive models , 1986, Advances in Applied Probability.

[20]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[21]  Neri Merhav,et al.  On the estimation of the order of a Markov chain and universal data compression , 1989, IEEE Trans. Inf. Theory.

[22]  A. Dale Magoun,et al.  Decision, estimation and classification , 1989 .

[23]  Neri Merhav,et al.  The estimation of the model order in exponential families , 1989, IEEE Trans. Inf. Theory.

[24]  Stanley L. Sclove,et al.  Application of the Conditional Population-Mixture Model to Image Segmentation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  H. Akaike.  A new look at the statistical model identification , 1974 .

[26]  J. W. Modestino,et al.  Use of the mean-field approximation in an EM-based approach to unsupervised stochastic model-based image segmentation , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[27]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[28]  Anil K. Jain,et al.  Markov Random Field Texture Models , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Haluk Derin,et al.  Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Jorma Rissanen,et al.  Universal coding, information, prediction, and estimation , 1984, IEEE Trans. Inf. Theory.

[31]  Chee Sun Won,et al.  Unsupervised segmentation of noisy and textured images using Markov random fields , 1992, CVGIP Graph. Model. Image Process..

[32]  R. Kashyap.  Inconsistency of the AIC rule for estimating the order of autoregressive models , 1980 .

[33]  R. Chellappa.  Two-Dimensional Discrete Gaussian Markov Random Field Models for Image Processing , 1989 .

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