Change detection (CD), which is a process of identifying changes occurred in a geographical area over the time, plays a key role in many applications including assessing natural disasters, monitoring crops, and managing water resources. In the past decades many CD (both binary and multiple) techniques have been proposed. Hence, evaluating and analyzing of probability of changes and interpreting them, is essential task which leads to better management of natural resources and preventing disasters. For this purpose, we adopted an approach to visualize probability of occurring detected changes. Based on this approach, change pixels will be categorized and labeled as probabilities (in percentage). In this paper, the proposed framework consists of the following three steps. Firstly, this research produces binary change maps from methods have been proposed in the literature. Then spectral similarity of pixels is calculated in abundances map (of endmembers) domain. A measurement of spectral similarity identifies the finer spectral differences between the two hyperspectral images (HSIs). Finally, combining binary map and spectral similarity values resulting change multiple probability map. The experimental results show that the method has a good result, and can be widely used in hyperspectral CD applications.