1. Introduction
The volume of remotely sensed imagery continues to grow at an enormous rate due to advances
in sensor technology for both high spatial and temporal resolution systems. As an example,
NASA’s Earth Observing System (EOS) is projected to receive one terabyte of image data per
day when fully operational. However, most existing information systems for managing remote
sensing imagery allow only simple queries based on sensor type, geographical location, and date
of capture. Building an information mining system to efficiently retrieve useful hidden patterns
from large remotely sensed image databases becomes a challenge.