I am trying to classify Landsat 8 MS data for some application. Im using ERDAS IMAGINE 2013 software tool for the same. The tool, however, provides an option for using non-parametric rules (parallepiped and feature space). I am unable to understand how these rules work , and what is their significance in classification. I am observing significant changes in classification accuracy with the use of non-parametric rules. Can someone tell me how to understand these rules. Also, where can I find the mathematical analysis of using these rules.
Normal distributions are important in statistics. Parametric algorithms (i.e.k-nearest neighbors) assume a normal distribution of the data. But, Nonparametric algorithms refer to a statistical method wherein the data is not required to fit a normal distribution. For example, SVM approach uses spectral or spatial remotely sensed information without consideration of their distributions. So, if you want to use spatial information( texture I mean!!) , for example, you have to use nonparametric methods such as SVM, ANN, RF and etc.
- Badges
- Science topic
- Similar topics
- Biological Science
- Anatomy
- Tissue