Home       Chase County Overview       Makesig       Maxlike       Mindist       Piped       Cluster       Isocluster   Results       References

  


Isocluster


Isocluster is another unsupervised classification technique. Isocluster classifies a multi band input image iteratively to the nearest cluster mean. It requires one to specify the bands to be processed and a composite image for seeding the cluster.

Operating the isocluster module I entered bands 1–5 and 7 for processing, and chose the 234 byte binary composite for seeding. I chose 3 iterations, 16 clusters, and titled the output image Isocluster Image. I studied this 16-cluster image to determine which of the clusters were associated with crops, forest, grassland, pavement, soil, and water. I then used reclass to group the 16 clusters into 6 clusters which were associated with the crops, forest, grassland, pavement, soil, and water classes. I then created this image with the six clusters appropriately labeled as the features they represented.


The isocluster classification gave more promising results than cluster had. The only two major discrepancies with isocluster were that bare fields were labeled as waterbodies and forest/riparian vegetation was mislabeled as crop fields.


This pie graph displays a statistical summary of the isocluster classification results.


  

Home       Chase County Overview       Makesig       Maxlike       Mindist       Piped       Cluster       Isocluster   Results       References