Abstract
The application of remote sensing data as a new source to update geographical information systems (GIS) has become increasingly popular in recent years. Meanwhile, there have been attempts to use GIS to improve the classification accuracy of remote sensing images. Although efforts have been made to use texture and context information, there are some limitations that apply to these methods. This paper proposes a new method to integrate GIS so that the shape information, which is frequently used in visual interpretation, can be employed easily to improve the performance of classification. The confusion of classification can be reduced significantly after shape information is involved.
| Original language | English |
|---|---|
| Pages (from-to) | 1473-1481 |
| Number of pages | 9 |
| Journal | International Journal of Remote Sensing |
| Volume | 17 |
| Issue number | 8 |
| DOIs | |
| State | Published - May 1996 |
| Externally published | Yes |