Text detection and recognition for semantic mapping in indoor navigation

Abstract

This paper presents a novel way for detecting sign board and text recognition to aid navigation in indoor environment. Using text as a landmark for vision based navigation is still an active research and till date all algorithms developed for detection and recognition of texts for an indoor navigation have a lot of room to make it applicable on real time. Our proposed method is an extension of the work and will aid in the on going research. We have achieved an accuracy of 80% and were able to extract sign boards text from actual scenes. Keywords: Text recognition, Robots, Image color analysis, Image edge detection, Navigation, Semantics, Indoor environments