Comparative Study of Segmentation and Recognition Methods for Handwritten Devnagari Script (original) (raw)

A Survey for Segmentation Techniques for Handwritten Devnagari Text Document

— Segmentation is one of the basic functions of handwritten Script Identification. Aside from the large variation of different handwriting its very difficult to segment the character from word. This paper give the short review on segmentation methods for handwritten character recognition. The aim is to provide an appreciation for the range of techniques that have been developed rather than to simply list sources. Various types of segmentation methods proposed for handwritten script identification include histogram based approach, average longest path approach, morphological approach, Junction based approach.

An efficient method of segmentation for handwritten devnagari word recognition

2015

Devnagari is the most popular and widely used script in India. It is used for writing Hindi, Marathi, Sanskrit and Nepali languages. Moreover, Devnagari script consists of vowels, consonants and various modifiers. Detection and extraction of text in images have been used in many applications. Document segmentation is one of the difficult and important phases in machine recognition of any language. The accuracy of character recognition engine depends on the correct segmentation of individual symbols. It is used to segment lines and words into sequence of characters into sub images of individual symbols. Hence proper segmentation of Devnagari word is challenging task. Especially the modifiers (both vowels and consonants) most of the time coincide with the modifying characters. These kinds of non-trivial combinations of characters make the whole process of character segmentation extremely challenging. Besides, some symbols, like ChandraBindu, often come between two consecutive characte...

Challenging Issues in Devanagari Script Recognition

2014

Rigorous research has been done on optical character recognition (OCR) and a large number of articles have been published on this topic during the last few decades. OCR plays a vital role in Digital Image Processing and Pattern Recognition. Numerous work has stated for Roman, Chinese, Japanese and Arabic scripts. There is no convenient work done on Indian script recognition. In India, more than 300 million people use Devanagari script for documentation. Although different efficient methodologies of Devanagari script recognition are proposed, but recognition accuracy of Devanagari script is not yet analogous to its overseas counterparts. This is predominantly due to the large variety of characters/symbols and their intimacy arrival in the Devanagari script. In this paper, we discuss some challenging issues which arise while recognition of Devanagari script. Keywords— OCR, image processing, peculiarities of the Devanagari script, challenging issues in

Offline Recognition of Devanagari Script: A Survey

IEEE Transactions on Systems, Man, and Cybernetics, 2011

In India, more than 300 million people use Devanagari script for documentation. There has been a significant improvement in the research related to the recognition of printed as well as handwritten Devanagari text in the past few years. State of the art from 1970s of machine printed and handwritten Devanagari optical character recognition (OCR) is discussed in this paper. All feature-extraction techniques as well as training, classification and matching techniques useful for the recognition are discussed in various sections of the paper. An attempt is made to address the most important results reported so far and it is also tried to highlight the beneficial directions of the research till date. Moreover, the paper also contains a comprehensive bibliography of many selected papers appeared in reputed journals and conference proceedings as an aid for the researchers working in the field of Devanagari OCR.

Script Segmentation of Printed Devnagari and Bangla Languages Document Images OCR

2011

In this Paper we focus on the line, word, character segmentation of printed Devnagari and Bangla script document for efficient recognition of the character. Devnagari and Bangla is the most popular script in the world. Script segmentation is very important step in the process of recognition of Indian languages document character. In the performance of script segmentation we have found 100% at line level script segmentation, 100% at world level script segmentation and approximately 100 % at character level segmentation of Devnagari and Bangla script document image after testing.

A Comparative study on Handwritten Devanagari Character Recognition

2020

Handwritten text recognition is a challenging task because of the vast changes in writing styles. In India, a massive number of people use Devanagari Script to write their documents, but due to large complexity, research work accomplished on this script is much lesser as compared to English script. Hence, recognition of handwritten Devanagari Script is amongst the most demanding research areas in the field of image processing. Feature extraction and recognition are key steps of OCR which affects the accuracy of the character recognition system. This paper gives a comparative study on distinct techniques used for feature extraction and classification by the researchers over the last few years.

Character Recognition of Offline Handwritten Devanagari Script Using Artificial Neural Network

2016

Document segmentation is one of the important phases in machine recognition of any language. Correct segmentation of individual symbols decides the exactness of character recognition technique. It is used to partitioned image of a string of characters into sub images of individual symbols by segmenting lines and words. Devnagari is the most accepted script in India. It is used for lettering Hindi, Marathi, Sanskrit and Nepali languages. Moreover, Hindi is the third most accepted language in the world. Devnagari documents consist of vowels, consonants and various modifiers. Hence perfect segmentation of Devnagari word is challenging. In this paper a bounded box method for segmentation of documents lines, words and characters and proper recognition of Devanagari characters using variation of Gradient, Structural features and artificial neural network (ANN) is proposed. KeywordsCharacter Segmentation, Character recognition, OCR System, Properties of Devanagari;

Recognition of Handwritten Devnagari Characters through Segmentation and Artificial neural networks

2012

Handwritten character recognition is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other devices.Handwritten Marathi Characters are more complex for recognition than corresponding English characters due to many possible variations in order, number, direction and shape of the constituent strokes. The main purpose of this paper is to introduce a new method for recognition of offline handwritten devnagari characters using segmentation and Artificial neural networks. The whole process of recognition includes two phases-segmentation of characters into line, word and characters and then recognition through feed-forward neural network.

A Segmentation-Free Approach for Printed Devanagari Script Recognition

Abstract—Long Short-Term Memory (LSTM) net- works are a suitable candidate for segmentation-free Optical Character Recognition (OCR) tasks due to their good context-aware processing. In this paper, we report the results of applying LSTM networks to De- vanagari script, where each consonant-consonant con- juncts and consonant-vowel combinations take different forms based on their position in the word. We also in- troduce a new database, Deva-DB, of Devanagari script (free of cost) to aid the research towards a robust De- vanagari OCR system. On this database, LSTM-based OCRopus system yields error rates ranging from 1.2% to 9.0% depending upon the complexity of the training and test data. Comparison with open-source Tesseract system is also presented for the same database.