%0 Journal Article %1 noauthororeditor %A Dongre, Vikas J %A Mankar, Vijay H %D 2011 %J International Journal of Computer Science, Engineering and Information Technology (IJCSEIT) %K Character Devnagari Line Machine Recognition Word learning paragraph segmentation %N 3 %P 46-53 %R 10.5121/ijcseit.2011.1305 %T DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH %U http://airccse.org/journal/ijcseit/papers/0811ijcseit05.pdf %V 1 %X Document segmentation is one of the critical phases in machine recognition of any language. Correct segmentation of individual symbols decides the accuracy of character recognition technique. It is used to decompose image of a sequence of characters into sub images of individual symbols by segmenting lines and words. Devnagari is the most popular script in India. It is used for writing Hindi, Marathi, Sanskrit and Nepali languages. Moreover, Hindi is the third most popular language in the world. Devnagari documents consist of vowels, consonants and various modifiers. Hence proper segmentation of Devnagari word is challenging. A simple histogram based approach to segment Devnagari documents is proposed in this paper. Various challenges in segmentation of Devnagari script are also discussed.

@article{noauthororeditor, abstract = {Document segmentation is one of the critical phases in machine recognition of any language. Correct segmentation of individual symbols decides the accuracy of character recognition technique. It is used to decompose image of a sequence of characters into sub images of individual symbols by segmenting lines and words. Devnagari is the most popular script in India. It is used for writing Hindi, Marathi, Sanskrit and Nepali languages. Moreover, Hindi is the third most popular language in the world. Devnagari documents consist of vowels, consonants and various modifiers. Hence proper segmentation of Devnagari word is challenging. A simple histogram based approach to segment Devnagari documents is proposed in this paper. Various challenges in segmentation of Devnagari script are also discussed. }, added-at = {2018-11-23T08:26:43.000+0100}, author = {Dongre, Vikas J and Mankar, Vijay H}, biburl = {https://www.bibsonomy.org/bibtex/2108d9c71ebf4a83e13f48d2fde77cc76/ijcseit}, doi = {10.5121/ijcseit.2011.1305}, interhash = {cd93706baa6f7c6a4f48a1732c9785b5}, intrahash = {108d9c71ebf4a83e13f48d2fde77cc76}, issn = {2231-3117 [Online] ; 2231-3605 [Print]}, journal = {International Journal of Computer Science, Engineering and Information Technology (IJCSEIT)}, keywords = {Character Devnagari Line Machine Recognition Word learning paragraph segmentation}, language = {English}, month = {August}, number = 3, pages = {46-53}, timestamp = {2018-11-23T08:26:43.000+0100}, title = {DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH}, url = {http://airccse.org/journal/ijcseit/papers/0811ijcseit05.pdf}, volume = 1, year = 2011 }