Cafcam: Crisp And Fuzzy Classification Accuracy Measurement Software

Introduction Classification is a fundamental image processing operation to extract information from remote sensing data. Both crisp and fuzzy classifications may be performed. In a crisp classification, each image pixel is assumed to be pure and is classified to one class. Often, particularly in coarse spatial resolution images, the pixels may be mixed containing two or more classes. Fuzzy classifications may be beneficial where a mixed pixel may be assigned multiple class memberships. Both supervised and unsupervised classification approaches may be followed. Generally, supervised classification is adopted involving three distinct stages; training, allocation and testing.