Some further results of three stage ML classification applied to remotely sensed images

Abstract Recently, a three stage Maximum Likelihood (TSML) classifier (N.B. Venkateswarlu and P. S. V. S. K. Raju, Pattern Recognition24, 1113–1116 (1991)) has been proposed to reduce the computational requirements of the ML classification rule. Some modifications are proposed here further to improve this fast algorithm. The Winograd method is proposed for use with range calculations, and is also used with Lower Triangular and Unitary canonical form approaches (W. Eppler, IEEE Trans. Geoscience Electronics14(1), 26–33 (1976)) in calculating quadratic forms. New types of range are derived by expanding the discriminant function which are then used with a TSML algorithm to identify their usefulness in eliminating groups at stages I and II. The use of pre-calculated values is proposed to obviate some multiplications while calculating the ranges. Further, threshold logic (A. H. Feiveson, IEEE Trans. Pattern Analysis Mach. Intell.5(1), 48–54 (1983)) is used with an old and a modified TSML classifier and its effectiveness observed in further reducing computation time. Performance of the old and the modified TSML algorithms is studied in detail by varying the dimensionality and number of samples. For the purpose of experiment, 6 channel thematic mapper (TM) and randomly generated 12 dimensional data sets are used. A maximum speed-up factor of 4–8 is observed with these data sets. These experiments are also repeated with modified maximum likelihood and Mahalanobis distance classifiers to inspect CPU time requirements.

[1]  David A. Landgrebe,et al.  Fast likelihood classification , 1991, IEEE Trans. Geosci. Remote. Sens..

[2]  D. Landgrebe,et al.  The K-L Expansion as an Effective Feature Ordering Technique for Limited Training Sample Size , 1983, IEEE Transactions on Geoscience and Remote Sensing.

[3]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[4]  S. Lampert,et al.  Multivariate Interactive Digital Analysis System (MIDAS): A New Fast Multispectral Recognition System , 1973 .

[5]  N. B. Venkateswarlu,et al.  A new fast classifier for remotely sensed imagery , 1993 .

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

[7]  M. Hodgson.  Reducing the computational requirements of the minimum-distance classifier , 1988 .

[8]  S. Sharma,et al.  A comparative study of supervised classifiers on a subscene in Junagadh district, Gujarat , 1990 .

[9]  Richard Harter.  The optimality of Winograd's formula , 1972, CACM.

[10]  D. Landgrebe,et al.  Feature Selection with Limited Training Samples , 1983, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Walter Eppler,et al.  Canonical Analysis for Increased Classification Speed and Channel Selection , 1976, IEEE Transactions on Geoscience Electronics.

[12]  G. Zyskind.  Introduction to Matrices with Applications in Statistics , 1970 .

[13]  B. F. Merembeck,et al.  Directed Canonical Analysis And the Performance of Classifiers under Its Associated Linear Transformation , 1980, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Philip H. Swain,et al.  Purdue e-Pubs , 2022 .

[15]  K. S. Fu.  Special computer architecture for pattern recognition and image processing - An overview , 1899, AFIPS National Computer Conference.

[16]  D. E. Minskii,et al.  Fast Bayes classification of multispectral images , 1983 .

[17]  Howard Jay Siegel,et al.  Contextual Classification of Multispectral Remote Sensing Data Using a Multiprocessor System , 1980, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Paul M. Mather,et al.  A computationally-efficient maximum-likelihood classifier employing prior probabilities for remotely-sensed data , 1985 .

[19]  S. A. Briggs,et al.  Fast maximum likelihood classification of remotely-sensed imagery , 1987 .

[20]  P. M. Narendra,et al.  Feature Subset Selection in Remote Sensing , 1978 .

[21]  David A. Landgrebe,et al.  Hierarchical classifier design in high-dimensional numerous class cases , 1991, IEEE Trans. Geosci. Remote. Sens..

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

[23]  JACK BRYANT.  A fast classifier for image data , 1989, Pattern Recognit..

[24]  James C. Bezdek,et al.  Efficient Implementation of the Fuzzy c-Means Clustering Algorithms , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Alan H. Feiveson.  Classification by Thresholding , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Sean C. Ahearn,et al.  Data space volumes and classification optimization of SPOT and Landsat TM data , 1991 .

[27]  N. B. Venkateswarlu,et al.  Three stage ML classifier , 1991, Pattern Recognit..

[28]  Patrick L. Odell,et al.  Comparison of Some Classification Techniques , 1974, IEEE Transactions on Computers.

[29]  Yoshifumi Yasuoka,et al.  Utilization of a best linear discriminant function for designing the binary decision tree , 1991 .

[30]  N. B. Venkateswarlu,et al.  Winograd's method: a perspective for some pattern recognition problems , 1994, Pattern Recognit. Lett..

[31]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[32]  T. M. Lillesand,et al.  Rapid maximum likelihood classification , 1991 .