Map production and usable information in Geospatial information system have notable cost and time allocated that finally such information and decisions are based further activities, especially in urban areas. Updating data involves the development of a geospatial information system and use of it. Change detection process, provides context for updating information and the latest applications and challenging in many branches include: urban planning, the environment and other sciences of the earth. Common techniques that used to Change detection, usually are based on pixels. In this study, two binary mask and post classification comparison method was used in combination and then compared the results of the comparative method of classification. Binary mask is a combination of Fuzzy thresholding and Automatic thresholding method such Otsu, Then comparing the classifiers such as, maximum likelihood, support vector machines, nearest neighbor and neural networks were used. The data set is provided by a couple of acquired very high resolution images on the Azadshahr region, District 22 of Tehran city (Iran) by the Quickbird and GeoEye sensors in 2006 and 2011 respectively. This data set is characterized by 3 visible spectral bands (Blue, Green and Red). The results show that the proposed method in terms of qualitative and quantitative comparison showing the changes against the post classification comparison method was more accurate and the overall accuracy and Kappa coefficient by using neural networks to map the changes resulting from this method is the equivalent of 73.32 and 68.38. However, the accuracy of the post classification comparison for neural networks of 65.61 and 48.96 against the kappa coefficient is obtained.