Real time text localization for Indoor Mobile Robot Navigation

TL;DR

This paper presents a fast, real-time text localization method for indoor mobile robot navigation, utilizing morphological operators and machine learning to accurately detect text landmarks in complex scenes.

Contribution

A novel two-step text localization approach combining morphological operators and SVM classification for real-time indoor robot navigation.

Findings

High detection accuracy compared to existing methods

Fast processing suitable for real-time applications

Effective in complex indoor environments

Abstract

Scene text is an important feature to be extracted, especially in vision-based mobile robot navigation as many potential landmarks such as nameplates and information signs contain text. In this paper, a novel two-step text localization method for Indoor Mobile Robot Navigation is introduced. This method is based on morphological operators and machine learning techniques and can be used in real time environments. The proposed method has two steps. At First, a new set of morphological operators is applied with a particular sequence to extract high contrast areas that have high probability of text existence. Using of morphological operators has many advantages such as: high computation speed, being invariant to several geometrical transformations like translation, rotations, and scaling, and being able to extract all areas containing text. After extracting text candidate regions, a set of nine features are extracted for accurate detection and deletion of the regions that don't have text. These features are descriptors for texture properties and are computed in real time. Then, we use a SVM classifier to detect the existence of text in the region. Performance of the proposed algorithm is compared against a number of widely used text localization algorithms and the results show that this method can quickly and effectively localize and extract text regions from real scenes and can be used in mobile robot navigation under an indoor environment to detect text based landmarks.