• Home
  • Search
  • Text detection and recognition on traffic panel in roadside imagery
  • Cite Icon8
  • https://doi.org/10.1109/ictemsys.2017.7958768Copy DOI Icon

Text detection and recognition on traffic panel in roadside imagery

  • May 1, 2017
  • Sarwar Khan +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Text recognition has revolutionized the world of image processing and intelligent transportation system (ITS). It opened several possibilities to traditional ITS concept. Advancement in text recognition has made it possible to implement text recognition in ITS. Traffic panel text recognition, a real time application is considered as a key addition to the revolution in modern ITS. This research aims at developing real time application for traffic panel text recognition for English and Thai. Text recognition in this paper is based on Support vector Machine (SVM), KNN and maximally stable extremal regions (MSER). Traffic panel are extracted based on visual appearance. Based on traffic panel background, color mask is applied to remove non text candidates. Multi-level MSER is used for segmentation. Raw pixel value of segmented character is used as feature vector. This system is trained for English and Thai language and then tested on roadside images of traffic panels. The results of different kernels are compared with each other to select best possible kernel for SVM. SVM results are then compared with KNN to find best classifier for this problem. The result shows that proposed system is robust and performs well in challenging environment.

Similar Papers
  • Research Article
  • Citations111

Text Detection and Recognition on Traffic Panels From Street-Level Imagery Using Visual Appearance

  • Feb 01, 2014
  • IEEE Transactions on Intelligent Transportation Systems
  • Alvaro Gonzalez +2
  • Conference Article
  • Citations2

Detection of Street-Level Traffic Panels Based on Cascaded Color Segmentation

  • Aug 01, 2018
  • Jiefeng Guo +3
  • PDF
  • Research Article

A CONTENT DISCLOSURE AND TEXT IDENTIFICATION BASED ON ROAD-LEVEL SYMBOLISM USING TCH ALGORITHM

  • Feb 28, 2015
  • International Journal of Research -GRANTHAALAYAH
  • Ramya R +2
  • Conference Article
  • Citations5

Character segmentation on traffic panels using visual appearance from roadside imagery

  • Jan 01, 2017
  • Sarwar Khan +4
  • Research Article

A CONTENT DISCLOSURE AND TEXT IDENTIFICATION BASED ON ROAD-LEVEL SYMBOLISM USING TCH ALGORITHM

  • Jan 01, 2015
  • Zenodo (CERN European Organization for Nuclear Research)
  • R Manikandan
  • Conference Article

Text and Symbol Extraction in Traffic Panel from Natural Scene Images

  • Nov 01, 2017
  • Zhen-Mao Li +1
  • Conference Article
  • Citations18

Text recognition on traffic panels from street-level imagery

  • Jun 01, 2012
  • A Gonzalez +3
  • Conference Article
  • Citations8

Persian Text Based Traffic sign Detection with Convolutional Neural Network: A New Dataset

  • Oct 29, 2020
  • Saba Kheirinejad +2
  • Book Chapter

Optical Character Detection and Recognition for Image-Based in Natural Scene

  • Jan 01, 2018
  • Bochao Wang +4
  • Research Article
  • Citations6

Text Line Detection from Rectangle Traffic Panels of Natural Scene

  • Jan 01, 2018
  • Journal of Physics: Conference Series
  • Shiyuan Wang +2
  • Research Article
  • Citations2

Scene Text Detection and Recognition Using Maximally Stable Extremal Region

  • Dec 15, 2024
  • Journal of Applied Engineering and Technological Science (JAETS)
  • Golda Jeyasheeli P +3
  • Conference Article
  • Citations9

Text recognition using poisson filtering and edge enhanced maximally stable extremal regions

  • Jul 01, 2017
  • Jiji Mol +2
  • Conference Article
  • Citations11

A license plate segmentation algorithm based on MSER and template matching

  • Oct 01, 2014
  • Xi Yang +5
  • Book Chapter
  • Citations18

Automatic Detection and Recognition of Symbols and Text on the Road Surface

  • Jan 01, 2015
  • Jack Greenhalgh +1
  • Conference Article

A fast approach for traffic panel detection from natural scene images

  • Dec 01, 2016
  • Zhen-Mao Li +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.