Adaptive thresholding of texture towards white region normalization

Human colour vision has the ability to recover a measure of context-depende nt surface reflectance from observed areas. This can be seen as an analogue to radiometric corrections employed in remote sensing. Procedures based on human colour vision applied in the context of remote sensing could simplif y image preprocessing and classification. This study evaluates an algorithm based on Land's colour vision or 'retinex' theory. When tested on remotely sensed images, the algorithm had difficulty coping with the presence of im age texture. A new framework is presented that adapts Land's procedure to p rocessing of remotely sensed images using adaptive thresholding techniques.