Uncertainty measure is a key issue for knowledge discovery and data mining. Rough set theory (RST) is an important tool for measuring and handling uncertain information. Although many RST-based methods to measure system uncertainty have been investigated, the existing measures are not able to characterize well the imprecision of a rough set. To overcome the shortcomings, we present a well-justified measure of uncertainty based on discernibility capability of attributes. The theoretical analysis is backed up with numerical examples to prove that our new method does not only overcome the limitations of the existing measures but also consist with human cognition.