Text and Sign Recognition for Indoor Localization

In this paper, we propose a modular approach to estimate the position and rotation of any mobile robot more precisely in an indoor environment using text and sign recognition. The modular approach for the text and sign recognition is performed in a twofold method in figure 1. First is the detection of the region with texts and various signs in the image which is done by an object detection system. The second part is the character recognition, where the detected textual region from the image will be passed onto an optical character recognition engine(OCR) engine to be recognized. This modular approach can be modified at any point based on any mobile robot in an indoor environment with texts and signs to help localize its position and rotation.