#TITLE_ALTERNATIVE#
Classification with pixel-based and object-based methods were used to extract information about land cover from Landsat Thematic Mapper image. In pixel-based, supervised classification technique was performed using Maximum Likelihood and Minimum Distance methods for the classification process. On th...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/14352 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Classification with pixel-based and object-based methods were used to extract information about land cover from Landsat Thematic Mapper image. In pixel-based, supervised classification technique was performed using Maximum Likelihood and Minimum Distance methods for the classification process. On the other hand, in object-based, image were segmented to homogenous area by suitable parameters in some levels. The classification results were compared each other to evaluate the two classification methods. To get the accuracy, the same set of ground truth data were given. The accuracy of pixel-based classification with maximum likelihood method is 77.27% and for minimum distance method is 76.14%. Beside that, the accuracy for object-based classification is 86.52% for level 1, 82.02% for level 2, and 78.65% for level 3. Object-based method gave more accurate then the pixel-based (including the user’s and producer’s accuracy). So that thematic mapper with object-based approached give higher results. |
|---|