Classification by diagnosing all absorption features (CDAF) for the most abundant minerals in airborne hyperspectral images

EURASIP Journal on Advances in Signal Processing

Table 2 Results of classification and overall accuracy of CDAF method

Class name	Calcite	Buddingtonite	Kaolinite	Alunite	Silica
Number of Class Samples	15	13	43	27	32
Number of pixels classified correctly	11	13	43	27	32
Classification accuracy for each class (%)	73.33	100	100	100	100
Overall accuracy: 96.92% (126/130)