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.

Parallel joint transform correlator applied to Devanagari script recognition

Abstract: A novel, to our knowledge, scheme for a parallel joint transform correlator system is demonstrated by the introduction of a five-channel zone-plate image multiplicator combined with photographic referencing and is applied to the recognition of Devanagari script. For considering the script's specific features, a partial image was obtained by means of windowing with 25 x 25 pixels out of a 64 x 64 pixel image of full-size characters and was employed for correlation. A comprehensive measurement of all 38 fundamental characters, namely, 1444 correlation pairs, showed satisfactory discrimination performance.

An approach for character segmentation of handwritten Bangla and devanagari script

Abstract: In this paper a scheme for segmentation of unconstrained handwritten Devanagari and Bangla words into characters and its sub-parts is proposed. Firstly, the region above headline is identified by counting the number of white to black transitions in each row, which followed by its separation. Then the characters are segmented using fuzzy logic. For each column, the inputs to the fuzzy system are the location of first white pixel, thickness of the first black stroke, count of white pixels, and the run length count of white pixels.

A Roman to Devanagari Back-Transliteration Algorithm based on Harvard-Kyoto Convention

Abstract: Transliteration is the process to transcribe a script of one language into another, while, backward or back transliteration is converting back the transliterated text into its original script. The highly technical phonetic system of Sanskrit seems to have made the preparation of transliteration scheme quite arduous. This study is focused on development of a rule-based, grapheme model character alignment back-transliteration algorithm of Sanskrit script, transcribed ASCII(American Standard Code for Information Interchange)-encoded English to Devanagari, pursuant to the Harvard-Kyoto (HK) convention. Accordingly, the paper presents the context of the utility for such an algorithm. It also describes the various standard schemes available for transcribing Devanagari into Roman. A survey on the evolution of scripts in India suggests the Brahmi script as the foundation for the origin of variants like Devanagari. Since the nineteenth century, various transliteration schemes based on Roman script have evolved. The International Alphabet of Sanskrit Transliteration (IAST) schemes used diacritics to disambiguate phonetic similarities and seem to have induced much strenuous venture for the non-professionals. The ASCII-based, HK and its variant, Indian Language Transliteration (ITRANS) schemes do not use diacritics and hence accounted to be the simplest. Our rationale for the use of HK scheme, stem from its prime traits of Sanskrit Unicode encoding. We have also explained the Sanskrit alphabet and its classifications, which are incorporated into our proffered process. We appraise the complexity of our pseudo-coded algorithm and finally, we propose an extension of this work in the creation of similar tools, for other Indian languages that use the Devanagari script, such as Hindi and Marathi.

Deep ConvNet with Different Stochastic Optimizations for Handwritten Devanagari Character

Abstract: In this paper, we present a deep learning model to recognize the handwritten Devanagari characters, which is the most popular language in India. This model aims to use the deep convolutional neural networks (DCNN) to eliminate the feature extraction process and the extraction process with the automated feature learning by the deep convolutional neural networks. It also aims to use the different optimizers with deep learning where the deep convolution neural network was trained with different optimizers to observe their role in the enhancement of recognition rate. It is discerned that the proposed model gives a 96.00% recognition accuracy with fifty epochs. The proposed model was trained on the standard handwritten Devanagari characters dataset.

An Efficient Segmentation Scheme for the Recognition of Printed Devanagari Script

Abstract: In this paper we propose on the script segmentation of Devanagari character for efficient recognition of the character. Script segmentation is a very important step in the process of the recognition a Devanagari script document or and other script document. Segmentation process is allows the OCR system to classify the Devanagari or other characters to improve the accuracy of the script Line or character. At the time of script or character recognition we have found that incorrect segmentation leads to incorrect recognition. Segmentation phase includes line, word and character segmentation. At the time of Recognition or Identification of the Devanagari script, we have found a difficult problem to segment the Devanagari script. Devanagari characters or scripts, lines are touching with head line. Some character shapes are similar. There are above 300 compounds, modified and basic shapes. Hence in the Devanagari script segmentation is a very challenging task at the time of recognizing the character of script document. In this paper we have achieved above 99.5% average accuracy depending upon Devanagari script document.