Real time image enhancement and segmentation for sign/text detection

Abstract

A personal computer(pc)-based low-cost visual system that can detect and extract text regions in visual signs in the scene and recognize them for location awareness is described. It employs fast image enhancement and segmentation methods based on symmetric neighborhood filter and hierarchical-connected component analysis to extract written information on signboards, which appears in the scene. Our approach allows us to remove the undesired segments by analyzing their features, removing the perspective distortion and correcting the orientation for better detection using signboard boundary lines and corners, extract the words and characters. As the signboard may not contain only text but also may contain nontext illustrations, the systems classifies each text region inside the signboard as "text-only" and "sign-only" using Support Vector Machine (SVM) based classifiers. Experimental results show the robustness of our region-based detection algorithm over pixel-based algorithms.