Real time image enhancement and segmentation for sign/text detection

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-connec...

Full description

Saved in:
Bibliographic Details
Main Authors: Haritaoglu, E.D., Haritaoglu, I.
Format: Conference Proceeding
Language:English
Subjects:
Data mining
Image enhancement
Image segmentation
Information filtering
Layout
Mobile radio mobility management
Support vector machine classification
Support vector machines
Text recognition
Visual system
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2003.1247414