A Novel Approach for improving Post Classification Accuracy of Satellite Images by Using Majority Analysis

In past one year, due to climatic changes and some anthropogenic activities, the forests of Uttarakhand are burning. To identify damage caused by forest fires, an area Nainital district has been taken for study. Multi temporal Landsat 7 images were from April - 2020 – 2021. This paper shows a novel approach increase accuracy classified image. The Support Vector Machine classification is first done then improve image, post-classification technique called Majority Analysis applied. method helps classify unclassified pixel it also smoothens out boundary pixels, leading higher rate. improved significantly 2021 89.35% 98.71% 88.52% 99.76% respectively. change detection study showed drastic in barren land fires on contrary, forest, scarce shrub areas have decreased.