Scene Text Extraction with Edge Constraint and Text Collinearity

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 395
  • Download : 893
In this paper, we propose a framework for isolating text regions from natural scene images. The main algorithm has two functions: it generates text region candidates, and it verifies of the label of the candidates (text or non-text). The text region candidates are generated through a modified Kmeans clustering algorithm, which references texture features, edge information and color information. The candidate labels are then verified in a global sense by the Markov Random Field model where collinearity weight is added as long as most texts are aligned. The proposed method achieves reasonable accuracy for text extraction from moderately dicult examples from the ICDAR 2003 database.
Files in This Item
ICPR10.pdf(221.76 kB)Download


  • mendeley


rss_1.0 rss_2.0 atom_1.0