Segmentation of Text Lines and Characters in Ancient Tamil Script Documents using Computational Intelligence Techniques

Abstract

Document image segmentation is one of the critical phases in handwritten character recognition system. Correct segmentation of individual characters decides the accuracy of the recognition system. It is used to decompose the sequence of characters into individual characters to segmenting text lines and then words. Ancient Tamil scripts documents consist of vowels, consonants and various modifiers. Hence proper segmentation algorithm is required. In existing methods, segmentation of overlapping lines and characters are difficult. In order to overcome this problem, two methods are proposed one for line segmentation and another for character segmentation, first method uses projection profile and PSO for line segmentation. In second method combination of connected components along with nearest neighborhood methods are used to segment the characters. Experimental results show that these methods give better results when compared to other methods.