Topic
Devanagari
About: Devanagari is a research topic. Over the lifetime, 655 publications have been published within this topic receiving 7428 citations. The topic is also known as: Deva nagari & Hindi Script.
Papers published on a yearly basis
Papers
More filters
••
14 Jul 2018TL;DR: This paper focuses on techniques which facilitates segmentation in Devanagari script (Hindi) for offline handwritten words i.e. Headline detection in handwritten word images of Hindi for extracting upper and middle zone characters and cropping.
Abstract: In the advent of digital computers and era where work force is shifted to be inclined on robotic process, Optical Character Recognition (OCR) has immense potentials to ease some these processes. Segmentation is one of the pre-processing phases- the pivotal essence of the process where lingual scripts and their characteristics vary to a much larger extent. This paper focuses on techniques which facilitates segmentation in Devanagari script (Hindi) for offline handwritten words i.e. Headline detection in handwritten word images of Hindi for extracting upper and middle zone characters and cropping. Experiments are performed on the handwritten legal amount words ICDAR database [1] on 106 words by 80 writers and on Self created touching character database on 106 words by 15 writers. The proposed zoning technique i.e. CPT (Continuous pixel technique) and cropping techniques is implemented on 10070 and 530 legal amount words with 98.89% accuracy and 80.94% respectively.
1 citations
••
01 Jan 2017TL;DR: The proposed strategy using CNN attains an average identification rate of 93.64%, with 5-fold cross-validation, for these three scripts when isolated offline handwritten characters of these scripts were considered.
Abstract: Script identification in multi-lingual text images will help in improving the efficiency of many real life applications, such as sorting, transcription of multilingual documents and OCR. In this paper, we have presented a technique for identification of three scripts, namely, Devanagari, Gurmukhi and Roman. We have identified the script of text based on statistical features, namely, zoning features; diagonal features; intersection and open end points based features; peak extent based features and combinations of these features. For classification, we have used multiple classification techniques, namely, Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), and Convolutional Neural Network (CNN). The proposed strategy using CNN attains an average identification rate of 93.64%, with 5-fold cross-validation, for these three scripts when isolated offline handwritten characters of these scripts were considered.
1 citations
••
1 citations
••
TL;DR: The neural transliteration model in this work is based on a sequence-to-sequence neural network that is composed of two major components, an encoder that transforms source language words into a meaningful representation and the decoder that is responsible for decoding the target language words.
Abstract: Transliteration is the task of translating text from source script to target script provided that the language of the text remains the same. In this work, we perform transliteration on less explored Devanagari to Roman Hindi transliteration and its back transliteration. The neural transliteration model in this work is based on a sequence-to-sequence neural network that is composed of two major components, an encoder that transforms source language words into a meaningful representation and the decoder that is responsible for decoding the target language words. We utilize gated recurrent units (GRU) to design the multilayer encoder and decoder network. Among the several models, the multilayer model shows the best performance in terms of coupon equivalent rate (CER) and word error rate (WER). The method generates quite satisfactory predictions in Hindi-English bilingual machine transliteration with WER of 64.8% and CER of 20.1% which is a significant improvement over existing methods.
1 citations
•
01 Jan 1967
1 citations