<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The paper presents the algorithm for text line segmentation based on the oriented anisotropic Gaussian kernel. Initially, the document image is split into connected components achieved by bounding boxes. These connected components are cleared from redundant fragments. Furthermore, the binary moments are applied to each of these connected components evaluating local text skewing. According to this information the orientation of the anisotropic Gaussian kernel is set. After the algorithm application the boundary growing areas around connected components are established. These areas are of major importance for the evaluation of text line segmentation. For testing purposes, the algorithm is evaluated under different text samples. Comparative analysis between algorithm with and without orientation based on the anisotropic Gaussian kernel is made. The results show the improvement in the domain of text line segmentation.</p></abstract>

The paper presents the algorithm for text line segmentation based on the oriented anisotropic Gaussian kernel. Initially, the document image is split into connected components achieved by bounding boxes. These connected components are cleared from redundant fragments. Furthermore, the binary moments are applied to each of these connected components evaluating local text skewing. According to this information the orientation of the anisotropic Gaussian kernel is set. After the algorithm application the boundary growing areas around connected components are established. These areas are of major importance for the evaluation of text line segmentation. For testing purposes, the algorithm is evaluated under different text samples. Comparative analysis between algorithm with and without orientation based on the anisotropic Gaussian kernel is made. The results show the improvement in the domain of text line segmentation.

Text Line Segmentation with the Algorithm Based on the Oriented Anisotropic Gaussian Kernel

University of Belgrade, Technical Faculty Bor, V.J. 12, 19210 Bor, Serbia

Technical College Niš, Aleksandra Medvedeva 20, 18000 Niš, Serbia

Journal of Electrical Engineering

The paper presents the algorithm for text line segmentation based on the oriented anisotropic Gaussian kernel. Initially, the document image is split into...

Text Line Segmentation with the Algorithm Based on the Oriented Anisotropic Gaussian Kernel

Publié en ligne: 24 août 2013

Pages: 238 - 243

DOI: https://doi.org/10.2478/jee-2013-0034

Mots clés
moments, connected components, text skew, text line segmentation, anisotropic Gaussian kernel

This content is open access.

Text Line Segmentation with the Algorithm Based on the Oriented Anisotropic Gaussian Kernel

Publié en ligne: 24 août 2013

Pages: 238 - 243

DOI: https://doi.org/10.2478/jee-2013-0034

Mots clésmoments, connected components, text skew, text line segmentation, anisotropic Gaussian kernel

This content is open access.

Mots clés
moments, connected components, text skew, text line segmentation, anisotropic Gaussian kernel