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

  


Piped


Piped is a parallelepiped classifier. The supervised piped classification operation also uses signature files to classify features. Piped uses each signature file to determine the lowest and highest reflectance values. From the high and low values, a threshold for each signature file is then created and all pixels which fall within the threshold are assigned to the same class. The piped operation is the fastest of the classification operations, but it is often the least accurate.

Performing the piped operation, I defined the parallelepiped by a z-score of 2.58. I chose the z-score value hoping it would exclude only 1% of most outlying pixels. For signature files, I entered the crops, forest, grassland, pavement, soil, and water signature files previously created. I gave the resulting image an output file name and titled it Piped Classification.


This is the resulting image of the piped classification. As it shows, it left many of the pixels unclassified. Having this many unclassified pixels gave inaccurate classification results and was discouraging. It appears that the image pixels that were classified were classified correctly.


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


  

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