The paper represents a brief description of our system as one of the solutions to the problem of global topological localization for indoor environments. The experiment involves analyzing images acquired with a perspective camera mounted on a robot platform and applying a feature-based method (SIFT) and two main systems in order to search and classify the given images. To obtain acceptable results and improved performance improvement, the algorithm acquires two main maturity levels: one capable of running in real-time and taking care of the computers’ resources and the other one capable of classifying correctly the input images. One of the principal benefits of the developed system is a server-client architecture that brings efficiency to the table along with statistical methods that improve the quality of data with their design.