Title :
Text extraction using edge detection and morphological dilation
Author :
Li, Shutao ; Kwok, James T.
Author_Institution :
Coll. of Electr. & Inf. Eng., Hunan Univ., Changsha, China
Abstract :
In this paper, a method used to extract text regions from document images is proposed. It first finds edges by computing the gradient of each location. Then long edges, such as lines and isolated edges which are often due to noise, are removed. Finally, this edge map is morphologically dilated. Experimentally, the proposed method is robust to noise, skew and text orientation.
Keywords :
edge detection; feature extraction; image classification; image denoising; image morphing; image segmentation; optical character recognition; document segmentation; edge detection; image classification; long edge removal; mathematical morphology dilation operator; morphological dilation; noise induced feature removal; noise robustness; skew robustness; text orientation; text region extraction; Character recognition; Data mining; Educational institutions; Graphics; Image edge detection; Isolation technology; Noise robustness; Optical character recognition software; Publishing; Resonance light scattering;
Conference_Titel :
Intelligent Multimedia, Video and Speech Processing, 2004. Proceedings of 2004 International Symposium on
Print_ISBN :
0-7803-8687-6
DOI :
10.1109/ISIMP.2004.1434067
