One of issues of automated classification is how to describe vegetation category so that the computer can understand and makes classification accordingly to it. Such system of definition is suitable for conventional vegetation mapping by ground observation or visual image interpretation when the interpreter combines image and auxiliary information to classify an object. Base of supervised classification is statistics. Established classes from training sites calculate function. Unsupervised classification with a clustering technique provides automated grouping. But there is no way to establish a fixed relation between a cluster code and a certain vegetation category. The most powerful classification in common use is automated classification. The author has discovered several image invariants based on Graphical Analysis of the Spectral reflectance Curve of a pixel (GASC) . The invariant founded includes modulation of the spectral reflectance curve, total reflected radiance index and spectral angles.
Using GLI Simulated data of Ninh Thuan, Binh Thuan and Lam Dong provinces observed on March 1, 1996 has carried out the research. Moreover results of post classification interpretation suggest that time is consuming and a subjective process requires extensive ground truth data collection.
View full abstract