Analysis of Supervised Maximum Likelihood Classification for remote sensing image

Pushpendra Singh Sisodia, Vivekanand Tiwari, Anil Kumar

2014 · 200 citations · 2 references

Concepts

Abstract

In this paper, Supervised Maximum Likelihood Classification (MLC) has been used for analysis of remotely sensed image. The Landsat ETM+ image has used for classification. MLC is based on Bayes' classification and in this classificationa pixelis assigned to a class according to its probability of belonging to a particular class. Mean vector and covariance metrics are the key component of MLC that can be retrieved from training data. Classification results have shown that MLC is the robust technique and there is very less chances of misclassification. The classification accuracy has been achieved overall accuracy of 93.75%, producer accuracy 94%, user accuracy 96.09% and overall kappa accuracy 90.52%.

References

2