Optimization of the Gaussian Kernel Extended by Binary Morphology for Text Line Segmentation

Abstract

In this paper, an approach for text line segmentation by algorithm with the implementation of the Gaussian kernel is presented. As a result of algorithm, the growing area around text is exploited for text line segmentation. To improve text line segmentation process, isotropic Gaussian kernel is extended by dilatation. Furthermore, algorithms with isotropic and extended Gaussian kernels are examined and evaluated under different text samples. Results are given and comparative analysis is made for these algorithms. From the obtained results, optimization of the parameters defining extended Gaussian kernel dimension is proposed. The presented algorithm with the extended Gaussian kernel showed robustness for different types of text samples.