ENHANCED TECHNIQUES TO DETECT, RECOGNIZE AND EXTRACT TEXT ON ENGLISH TRAFFIC PANELS ALONG ROAD SIDE

Apply

 ENHANCED TECHNIQUES TO DETECT, RECOGNIZE AND EXTRACT TEXT ON ENGLISH TRAFFIC PANELS ALONG ROAD SIDE

Journal Title: International Journal of Engineering Sciences & Research Technology - Year 0, Vol 4, Issue 8

Abstract

 Traffic Panel Detection and Text Extraction is an important issue in road maintenance system. This is also important because it provides effective and secure medium to drivers to drive safely. Traffic Panels differ in appearance because of different size and style of text written on Traffic Panels. Language is also a problem for drivers. As language differs as we travel country to country and throughout the world. Detection of Traffic Panel also becomes difficult due to different variety of text appearance because of different fonts, thicknesses, colors, sizes, textures, as well as the presence of geometrical distortions and partial occlusions in the images, different lighting conditions and image resolutions, etc. This paper mainly deals with English Traffic Panels Detection and Extraction of text written on them. Firstly it detects a Proper English Traffic Panel from all the panels arriving along a road side and in second part it then extracts text from that panel. Finally, Text Detection and Recognition method is applied on those images where a traffic panel has been detected. Text detection and recognition in images is a system which attempts to develop a computer system with the ability to automatically read from images the text content visually embedded in complex backgrounds. This extracted text can then be used to help drivers to drive considering the safety issues.

Authors and Affiliations

Ms. Pallavi R. Vyas*

Keywords

EP ID EP137868
DOI -
Views 82
Downloads 0