Modified highest confidence first classification

A classification procedure is developed that distinguishes between pixels that are clearly associated with a given class versus those where class assignment is uncertain. Alternatively, most commonly used classification algorithms force each pixel into a single class without regard to certainty. By classifying pixels in order of certainty and considering spatial context, pixels with weak observational evidence for classification are prevented from contributing to their neighbor's decisions. Subsequently, a better decision is made for the uncertain pixels by considering the previously classified neighbors. Degrees of certainty measures can assist in later map accuracy assessment by allowing for stratified sampling of zones having similar certainty levels