<![CDATA[To maintain the availability of the patchouli plants required monitoring the spread of patchouli plantation. This study performed the identification of patchouli plant through Landsat-8 satellite imagery and Improved K-Means method. Improved was done on this study include the process of determining the initial cluster by specifying the closeness between the data and the determination of the number of cluster (K) by using the histogram equalization technique. The result of internal criteria testing shows that determining the number of clusters using the histogram is less effective because it produces the lower value of the silhouette. On almost all image data test found the best value of the silhouette's coefficient is 75.089% at K=2 and data in February. Furthermore, based on the results of testing the external criteria known the highest purity value in February data with a number of cluster 5 is 0.6829268. The test results also show that the use of the Improved K-Means on the Landsat-8 image has not been able to recognize the difference patchouli plants with other crops due to the limited resolution of imagery data and also the minimum number and variation of test data. But, visually the patchouli plant cluster is found for February data while the age of the rice crop surrounding the patchouli is still in the early phase of planting.]]>
Copyrights © 2016
