An improved edge-based text region segmentation algorithm applied to slab image data from steel plant

Authors:
SungHoo Choi;Jong Pil Yun;Bo Yeul Seo;JeeHoon Park;KeunHwi Koo;JongHyun Choi;Sang Woo Kim
Affiliations:
Pohang University of Science and Technology, Pohang, Korea;Pohang University of Science and Technology, Pohang, Korea;Pohang University of Science and Technology, Pohang, Korea;Pohang University of Science and Technology, Pohang, Korea;Pohang University of Science and Technology, Pohang, Korea;Pohang University of Science and Technology, Pohang, Korea;Pohang University of Science and Technology, Pohang, Korea
Venue:
CGIM '08 Proceedings of the Tenth IASTED International Conference on Computer Graphics and Imaging
Year:
2008

Citing 6
Cited 1

TextFinder: An Automatic System to Detect and Recognize Text In Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Parsing: Unifying Segmentation, Detection, and Recognition

International Journal of Computer Vision
Detection of text region and segmentation from natural scene images

ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Stroke-model-based character extraction from gray-level document images

IEEE Transactions on Image Processing
Automatic detection and recognition of signs from natural scenes

IEEE Transactions on Image Processing
Localizing and segmenting text in images and videos

IEEE Transactions on Circuits and Systems for Video Technology

Reliable algorithm for slab region localization using robust features

ISPRA'09 Proceedings of the 8th WSEAS international conference on Signal processing, robotics and automation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes about the extraction of the text regions. In steel making process, it is very important to recognize the product management numbers because workers use it to tell quality and uses of slabs. Therefore automatic extraction of the slab management numbers is a prerequisite for automatic character segmentation and recognition system. In these days, many researchers have studied about the automatic text region detection from natural scenes, video frames, etc. However, these algorithms are not well suited for the steel plant environment. In this paper, the detail process of an improved edge-based horizontal text region detection method is described. Based on the above process, the selective binarization and the iterative character estimation are performed to find both side boundaries of the text region. Experimental results show that proposed method is robust and has higher detection rate.