A comparative study of supervised classifiers on a subscene in Junagadh district, Gujarat
10.1007/BF03030729 Cite this article as: Oza, M.P. & Sharma, S.A. J Ind Soc Remote Sens (1990) 18: 18. doi:10.1007/BF03030729 Abstract
This paper describes the results of a comparative study of five classifiers viz., maximum likelihood, modified maximum likelihood, minimum distance to mean. Fisher and min-max, for classifying a subscene of Junagadh district using Landsat Thematic Mapper (TM) data. The kappa coefficient of agreement (k) and per cent correctly classified pixels for training data are used as measures of overall performance. It is observed that maximum likelihood and modified maximum likelihood classifiers perform better than the other three classifiers for this data set. Band combinations (3, 4, S) and (2, 3, 4, S) perform better than the usual combination (1,2,3,4), possibly because of presence of middle infrared band (band 5) on a scene dominated by vegetation cover. The band combination (1, 2, 3, 4, 5, 7) performed the best.
Beaubien J 1979. Forest type mapping from Landsat digital data.
Photogr. Engg. and Rem. Sens., 45, 1135–1144.
Chang J K and Dwyer S J, 1973. New multiclass classification method : Modified maximum likelihood decision rule.
Proceedings of the first International Joint Conference on Pattern Recognition. Washington D.C., October 30–November 1, 334–339.
Cohen J 1960. A coefficient of agreement for nominal scales.
Educational and Psychological Measurement
Craig R G. 1979. Autocorrelation in Landsat data.
Proceedings of the 13th Int. Symp. on Rem. Sens. Environment, Ann Arbor, Michigan, 1517–1524.
Craig R G and Labovitz M L 1980. Sources of variation in Landsat autocorrelation,
Proceedings of the 14th Int. Symp. on Rem. Sens, of Environment. Ann Arbor, Michigan, 1755–1767.
Dadhwal V K, Parihar J S, Medhavy D S, Ruhal D S and Jarwal S D 1987. Wheat acreage estimation of Haryana for 1986–87, using Landsat MSS data.
Scientific Note : IRS-UP/SAC/CPF/SN/ 15/87, 26.
Diaconis P and Efron B 1983. Computer intensive methods in statistics.
Geisser S 1981. Sample reuse procedures for prediction of the unobserved portion of a partially observed vector.
Haralick R M, Shanmugam K and Dinstein I 1973. Textural features for image classification,
IEEE Transactions on Systems, Man and Cybernetics
Hudson W D and Ramm C W 1987. Correct formulation of the kappa coefficient of agreement
Photogr. Engg. and Rem. Sens., 53, 421–422.
Jain A K, Dubes R C and Chen C 1987. Bootstrap techniques for error estimation.
IEEE Transactions on Pattern Analysis and Machine Intelligence
Jenson JR 1986.
Introductory digital image processing: a remote sensing perspective. Prentice-Hall, New Jersey.
Nelson R F, Latty R S and Mott G, 1984. Classifying northern forests using Thematic Mapper Simulator data.
Photogr. Engg. and Rem. Sens., 50, 607–617.
Potdar M B, Kalubarme M H, Sharma R, Biswas B C, Dubey RC and Bhandari S G 1987. Remote sensing based hectarage estimation of semi-arid tropical crops : A case study of 1986 rabi sorghum in Solapur district.
Scientific Note: IRS-UP/SAC/CPF/SN/14/87. 23p.
Rosenfield G H and Fitzpatrick-Lins R 1986. A coefficient of agreement as a measure of thematic classification accuracy,
Photo. Engg. and Rem. Sens, 52, 223–227.
Sheffield C 1985. Selecting band combinations from multispectral data.
Photogr. Engg. and Rem. Sens., 51, 681–687.
Skidmore A K and Turner B J 1988. Forest mapping accuracies are improved using a supervised nonparametric classifier with SPOT data.
Photogr. Engg. and Rem. Sens., 54, 1415–1421.