Approach to the Improvement of the Text Line Segmentation by Oriented Anisotropic Gaussian Kernel
Darko Brodić, Zoran Milivojević, Dragan Milivojević · Elektronika ir Elektrotechnika · 2012
The paper presents the approach to the algorithm for text line segmentation based on the anisotropic Gaussian kernel. As a result of this algorithm the growing region around text is exploited. Furthermore, anisotropic Gaussian kernel is rotated to improve text line segmentation process. Text objects orientation is evaluated by binary moments. For test purposes algorithm is evaluated under different text samples. From the obtained results comparative analysis between algorithm with anisotropic and oriented Gaussian kernel is made. At the end, benefits of the extended approach are revealed. Ill. 7, bibl. 22, tabl. 5 (in English; abstracts in English and Lithuanian).DOI: http://dx.doi.org/10.5755/j01.eee.118.2.1181