Layered classification offers several advantages over the very familiar single-stage approach. The single-stage method of pattern classification utilizes all available features in a single test which assigns the "unknown" to a category according to a specific decision strategy (such as the maximum likelihood strategy). The layered classifier classifies the "unknown" through a sequence of tests, each of which may be dependent on the outcome of previous tests. Although the layered classifier was originally investigated as a means of improving classification accuracy and efficiency, it has become apparent that in the context of remote sensing data analysis, other advantages also accrue due to many of the special characteristics of both the data and the applications pursued. This paper outlines the layered classifier method and discusses several of the diverse applications to which this approach is well suited.
展开▼
