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

  


Maxlike

One supervised classification technique employed to differentiate between surface features is Maxlike. Maxlike uses a Maximum Likelihood classification based on information contained in a set of signature files. The maximum likelihood classification is determined by the probability density function associated with the training site signature. Pixels are assigned to the appropriate class based on a comparison of the posterior probability that it applies to each of the signatures being considered.

Using the maxlike operation, I indicated that equal prior probabilities should be used. For the classification, I entered the crops, forest, grassland, pavement, soil, and water signature files previously created. I indicated 0% as the proportion to exclude, classifying all pixels. Finally I entered an output image and titled it Maxlike Classification.


This is the resulting image of the maxlike classification. It is fairly accurate with no major discrepancies.


Also, using Idrisi’s AREA module I determined the area of each class in square kilometers. Using the area results, I created this pie graph to display maxlike's surface feature breakdown of Chase County.




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