SnooperText: A Multiresolution System for Text Detection in Complex Visual Scenes

From LRDE

Abstract

Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are then filtered out using shapebased classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results


Bibtex (lrde.bib)

@InProceedings{	  minetto.10.icip,
  author	= {Rodrigo Minetto and Nicolas Thome and Matthieu Cord and
		  Jonathan Fabrizio and Beatriz Marcotegui},
  title		= {SnooperText: A Multiresolution System for Text Detection
		  in Complex Visual Scenes},
  booktitle	= {Proceedings of the IEEE International Conference on Image
		  Processing (ICIP)},
  pages		= {3861--3864},
  year		= 2010,
  address	= {Hong Kong},
  month		= sep,
  abstract	= {Text detection in natural images remains a very
		  challenging task. For instance, in an urban context, the
		  detection is very difficult due to large variations in
		  terms of shape, size, color, orientation, and the image may
		  be blurred or have irregular illumination, etc. In this
		  paper, we describe a robust and accurate multiresolution
		  approach to detect and classify text regions in such
		  scenarios. Based on generation/validation paradigm, we
		  first segment images to detect character regions with a
		  multiresolution algorithm able to manage large character
		  size variations. The segmented regions are then filtered
		  out using shapebased classification, and neighboring
		  characters are merged to generate text hypotheses. A
		  validation step computes a region signature based on
		  texture analysis to reject false positives. We evaluate our
		  algorithm in two challenging databases, achieving very good
		  results},
  keywords	= {Text detection, multiresolution, image segmentation,
		  machine learning}
}