Contiguity-enhanced k-means clustering algorithm for unsupervised multispectral image segmentation

The recent and continuing construction of multi- and hyper-spectral imagers will provide detailed data cubes with information in both the spatial and spectral domain. This data shows great promise for remote sensing applications ranging from environmental and agricultural to national security interest. The reduction of this voluminous data to useful intermediate forms is necessary both for downlinking all those bits and for interpreting them. Smart on-board hardware is required, as well as sophisticated earth-bound processing. A segmented image is one kind of intermediate form which provides some measure of data compression. Traditional image segmentation algorithms treat pixels independently and cluster the pixels according only to their spectral information. This neglects the implicit spatial information that is available in the image. We will suggest a simple approach - a variant of the standard k-means algorithm - which uses both spatial and spectral properties of the image. The segmented image has the property that pixels which are spatially continuous are more likely to be in the same class than are random pairs of pixels. This property naturally comes at some cost in terms o of the compactness of the clusters in the spectral domain,but we have found that the spatial contiguity and spectral compactness properties are nearly 'orthogonal', which means that we can make considerable improvements in the one with minimal loss in the other.

[1]  Luis Torres,et al.  ANALYSIS AND OPTIMIZATION OF THE K-MEANS ALGORITHM FOR REMOTE SENSING APPLICATIONS , 1992 .

[2]  Vittorio Castelli,et al.  On the exponential value of labeled samples , 1995, Pattern Recognit. Lett..

[3]  Geoffrey H. Ball,et al.  ISODATA, A NOVEL METHOD OF DATA ANALYSIS AND PATTERN CLASSIFICATION , 1965 .

[4]  Fionn Murtagh,et al.  Cluster Dissection and Analysis: Theory, Fortran Programs, Examples. , 1986 .

[5]  G. Gisler,et al.  Spatio-spectral image analysis using classical and neural algorithms , 1996 .

[6]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[7]  Anil K. Jain,et al.  A spatial filtering approach to texture analysis , 1985, Pattern Recognit. Lett..

[8]  Frederick R. Fromm,et al.  Class: A nonparametric clustering algorithm , 1976, Pattern Recognit..

[9]  Francisco F. Rivera,et al.  Parallel Squared Error Clustering on Hypercube Arrays , 1990, J. Parallel Distributed Comput..

[10]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1987, Computer.

[11]  Anil K. Jain,et al.  Clustering techniques: The user's dilemma , 1976, Pattern Recognit..

[12]  William M. Rand,et al.  Objective Criteria for the Evaluation of Clustering Methods , 1971 .

[13]  Anil K. Jain,et al.  A VLSI Systolic Architecture for Pattern Clustering , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  William Equitz,et al.  A new vector quantization clustering algorithm , 1989, IEEE Trans. Acoust. Speech Signal Process..

[15]  G. McLachlan,et al.  Updating a discriminant function in basis of unclassified data , 1982 .

[16]  E. Forgy.  Cluster analysis of multivariate data : efficiency versus interpretability of classifications , 1965 .

[17]  H. Spath.  The Cluster Dissection and Analysis Theory FORTRAN Programs Examples , 1985 .

[18]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[19]  K. Chidananda Gowda.  A feature reduction and unsupervised classification algorithm for multispectral data , 1984, Pattern Recognit..

[20]  Terence J. O'Neill.  Normal Discrimination with Unclassified Observations , 1978 .

[21]  Alan P. Schaum,et al.  Application of stochastic mixing models to hyperspectral detection problems , 1997, Defense, Security, and Sensing.

[22]  D. M. Titterington,et al.  Updating a Diagnostic System using Unconfirmed Cases , 1976 .