Devanagari Research Articles

Using IndoWordNet for Contextually Improved Machine Translation of Gujarati Idioms

Gujarati language is the Indo-Aryan language spoken by the Gujaratis, the people of the state of Gujarat of India. Gujarati is the one of the 22 official languages recognized by the Indian government. Gujarati script was adopted from Devanagari script. Approximately 3000 idioms are available in Gujarati language. Machine translation of any idiom is the challenging task because contextual information is important for the translation of a particular idiom. For the translation of Gujarati idioms into English or any other language, surrounding contextual words are considered for the translation of specific idiom in the case of ambiguity of the meaning of idiom. This paper experiments the IndoWordNet for Gujarati language for getting synonyms of surrounding contextual words. This paper uses n-gram model and experiments various window sizes surrounding the particular idiom as well as role of stop-words for correct context identification. The paper demonstrates the usefulness of context window in case of ambiguity in the meaning identification of idioms with multiple meanings. The results of this research could be consumed by any destination-independent machine translation system for Gujarati language.

TOWARDS CRITICAL EDITION OF LOLIMBARAJA’S VAIDYA-JEEVANA INCORPORATING THE IMPORTANT COMMENTARIES DEEPIKA BY RUDRABHATTA AND GUDARTHA DEEPIKA BY HARINATH GOSWAMI

The manuscripts preserved acts as valuable treasure of knowledge which can be utilized for the wellbeing of present generation as well as to pass on to the next generation. A thorough study on Deepika and Gudartha Deepika commentaries on Lolimbaraja's Vaidya jeevana, present in the form of manuscript in oriental research institute libraries has been brought much information that is new for present understanding. The present study focuses on treatment aspects of various diseases and preparation of yogas with easy available drugs in present clinical practice and better development of Ayurvedic practices. The study is based on the technical method of critical edition in order to update & conserve the medical knowledge dealt in Deepika and Gudartha Deepika commentaries on Lolimbaraja's Vaidya jeevana. Objective: 1. To collect and decipher two important commentaries on Lolimbarajas vaidya Jeevana 2. To collate and critically edit the two important commentaries on Lolibarajs Vaidya Jeevana to know their contributions. Methodology: The study is based on seven plus five (total 12) manuscripts and all were in Devanagari script and their details are as below. 1. R-1 to R 7 are - Obtained from BORI, Pune : Acession numbers as - 1093/ 1886-92, 463/ 1895-98, 353/ 1879-80, 948/ 1891-95, 178/ 1882-83, 618/ Vi¾-1, 306/ Vi¾.1 2. H-1 to H 4 are -Obtained from BORI, Pune; Accession numbers as- 462/1895-98, 913/ 1887-91, 635/ 1895-1902, 238.B/ A 1883-84 and IX 3. H-5 - Obtained from Zen library, Arrah, Bihar; Accession number 76/42. Digitization of manuscripts, editing and analysis of mutual relationship among collected copies of Manuscripts, transliteration of all extant of copies selected for Critical edition and Critical Edition with English Translation of the Text is being done. Conclusion By observing all internal and external evidences, Deepika by Rudrabhatta and Gudartha Deepika by Harinatha Goswami are the well known commentaries on Lolimbaraja’s Vaidya jeevana pertaining to early and late 17th CAD respectively. These all contributions enhance the richness of Ayurveda in modern era. KEYWORDS: Critical edition, Deepika, Rudrabhatta, Gudartha Deepika, Goswami Harinatha, Vaidya Jeevana, etc.

Recognising Devanagari Script by Deep Structure Learning of Image Quadrants


 
 
 Ancient Indic languages were written in the Devanagari script from which most of the modern-day Indic writing systems have evolved. The digitisation of ancient Devanagari manuscripts, now archived in national museums, is a part of the language documentation and digital archiving initiative of the Government of India. The challenge in digitizing these handwritten scripts is the lack of adequate datasets for training machine learning models. In our work, we focus on the Devanagari script that has 46 categories of characters that makes training a difficult task, especially when the number of samples are few. We propose deep structure learning of image quadrants, based on learning the hidden state activations derived from convolutional neural networks that are trained separately on five image quadrants. The second phase of our learning module comprises of a deep neural network that learns the hidden state activations of the five convolutional neural networks, fused by concatenation. The experiments prove that the proposed deep structure learning outperforms the state of the art.
 
 

NN-based analytic approach to symbol level recognition for degraded Bengali printed documents

Analysis of degraded printed documents has been a research topic for last several years. In this article the contribution lies in segmentation of word images into symbols and recognition of the symbols of degraded printed document images of Bengali, the 7th most popular language in the world. A novel approach to symbol level segmentation based on a Multilayer Perceptron (MLP) network is proposed. A database of segmenting and non-segmenting image columns is developed from the ISIDDI page level database and segmentation is treated as a two-class classification problem. The MLP weights are learnt based on this database using the back propagation algorithm. We have introduced certain new metrics, based on which the F-score of the proposed segmentation algorithm is determined. Our method utilizes information that is relevant for character segmentation, ignoring other highly variable information contained in a printed text document, thus allowing for efficient transfer learning between datasets and alleviating the need for labelled training data. Other than Bengali, we have tested on English, Tamil and Devnagari scripts. For the classification purpose we have identified 336 symbols, and the corresponding training and test sets have been developed. The ISIDDI database is used for this purpose. Two classifiers, one CNN based and the other LSTM based, have been developed for this 336-class problem. The classification accuracies obtained on the test set by the CNN classifier and the LSTM classifier are 86.05% and 88.11%, respectively. The proposed classifiers outperform the existing classifiers for the ISIDDI database.

Comparative Analysis of Segmentation and Recognition Techniques for Offline Handwritten Words

A Pre-processing is the initial and vital phase in optical character recognition is the Pre-processing. Segmentation deals with the extraction of individual component from a document image. Number of techniques like projection profile, connected components, gaps between characters/components is reported in the literature for component extraction followed by feature extraction and recognition of the individual component. These techniques gives good results if components are isolated but fails if components are touched, shadowed or skewed. A novel technique is required to address such issues to enhance the recognition rate. The problem of segmentation for Roman script cursive handwriting is addressed by various authors but not enough addressed for Indian script especially Devanagari script. This paper is a review which is confined to offline handwritten script domain. It attempt to review various techniques for character segmentation considering touching characters for offline handwritten words in Devanagari script and scripts sharing similar characteristics (like Bangla, Gurumukhi), database used and their accuracy reported in the literature.

Word and Chracter Segmentation in Devnagari and Odia Script – A Comparitive Analysis

Optical Character Recognition has been an active research area in computer science for several years. Several research works undertaken on various languages in India. In this paper an attempt has been made to find out the percentage of accuracy in word and character segmentation of Hindi (National language of India) and Odia is one of the Regional Language mostly spoken in Odisha and a few Eastern India states. A comparative article has been published under this article. 10 sets of each printed Odia and Devanagari scripts with different word limits were used in this study. The documents were scanned at 300dpi before adopting pre-processing and segmentation procedure. The result shows that the percentage of accuracy both in word and character segmentation is higher in Odia language as compared to Hindi language. One of the reasons is the use of headers line in Hindi which makes the segmentation process cumbersome. Thus, it can be concluded that the accuracy level can vary from one language to the other and from word segmentation to that of the character segmentation.

Natural Language Processing Based Sentimental Analysis of Hindi (SAH) Script an Optimization Approach

Sentimental analysis is one of the most common applications of Natural Language Processing (NLP). Sentiment analysis, the term itself refers to identify the emotions and opinions of people through written text. It is concerned with information extraction from any text based on the polarity in social behavior whether it may be positive, negative or neutral. This paper presents a practical dynamic approach on to find the polarity of any sentence and analyse the opinion of the particular sentence. The proposed Sentimental Analysis of Hindi (SAH) script have adopted two different classifier Naive Bayes Classifier and Decision Tree Classifier is used for the text extraction. The positive, neutral and negative result validation shows a comparative result of sentimental analysis.

Review for Handwritten Devanagari Character Recognition using ML Algorithms

Devanagari Character Recognition is a system in which handwritten Image is recognized and converted into a digital form. Devanagari handwritten character recognition system is based on Deep learning technique, which manages the recognition of Devanagari script particularly Hindi. This recognition system mainly has five stages i.e. Pre-processing, Segmentation, Feature Extraction, Prediction and Post processing. This paper has analyzed the approach for recognition of handwritten Devanagari characters. There are various approaches to solve this. Some of the methods along with their accuracy and techniques used are discussed here. Depending upon the dataset and accuracies of each character the techniques differs.

Measuring Performance of Generative Adversarial Networks on Devanagari Script

The working of neural networks following the adversarial philosophy to create a generative model is a fascinating field. Multiple papers have already explored the architectural aspect and proposed systems with potentially good results however, very few papers are available which implement it on a real-world example. Traditionally, people use the famous MNIST dataset as a Hello, World! example for implementing Generative Adversarial Networks (GAN). Instead of going the standard route of using handwritten digits, this paper uses the Devanagari script which has a more complex structure. As there is no conventional way of judging how well the generative models perform, three additional classifiers were built to judge the output of the GAN model. The following paper is an explanation of what this implementation has achieved.

Recognition of Offline Handwritten Characters using 2D FFT for English and Hindi Scripts

The Handwritten Character Recognition has been a challenging task for the past many decades. This is an old application related to the area of pattern recognition. Handwritten character recognition (HCR) can be classified into two types namely, Online and Offline. As per the literature survey, there are no standard databases for HCR [1] [2] [3] since there are very less number of speakers for any Indian language compared to English. Hence, the database of Indian scripts both for testing and training are to be developed in the laboratory environment. The recognition accuracy for printed / typed characters is more than 99 percent, whereas for the HCR it is around 60 percent. Hence the area of HCR is an open area of research. HCR for Indian languages is at nascent stage compared to English since they contain alphabets and also matra’s / sandhi are complex which make the recognition tougher. The freedom of the scriber in writing the script is also another challenge for achieving the better recognition accuracy. This work describes the handwritten character recognition of both Hindi and English scripts by extracting features using 2D FFT and using the Nearest Neighborhood Classifier. The best recognition accuracy for handwritten character recognition of English and Hindi languages obtained is 70%.

DevNet: An Efficient CNN Architecture for Handwritten Devanagari Character Recognition

The writing style is a unique characteristic of a human being as it varies from one person to another. Due to such diversity in writing style, handwritten character recognition (HCR) under the purview of pattern recognition is not trivial. Conventional methods used handcrafted features that required a-priori domain knowledge, which is always not feasible. In such a case, extracting features automatically could potentially attract more interests. For this, in the literature, convolutional neural network (CNN) has been a popular approach to extract features from the image data. However, state-of-the-art works do not provide a generic CNN model for character recognition, Devanagari script, for instance. Therefore, in this work, we first study several different CNN models on publicly available handwritten Devanagari characters and numerals datasets. This means that our study is primarily focusing on comparative study by taking trainable parameters, training time and memory consumption into account. Later, we propose and design DevNet, a modified CNN architecture that produced promising results, since computational complexity and memory space are our primary concerns in design.

Ancient text recognition: a review

Optical character recognition (OCR) is an important research area in the field of pattern recognition. A lot of research has been done on OCR in the last 60 years. There is a large volume of paper-based data in various libraries and offices. Also, there is a wealth of knowledge in the form of ancient text documents. It is a challenge to maintain and search from this paper-based data. At many places, efforts are being done to digitize this data. Paper based documents are scanned to digitize data but scanned data is in pictorial form. It cannot be recognized by computers because computers can understand standard alphanumeric characters as ASCII or some other codes. Therefore, alphanumeric information must be retrieved from scanned images. Optical character recognition system allows us to convert a document into electronic text, which can be used for edit, search, etc. operations. OCR system is the machine replication of human reading and has been the subject of intensive research for more than six decades. This paper presents a comprehensive survey of the work done in the various phases of an OCR with special focus on the OCR for ancient text documents. This paper will help the novice researchers by providing a comprehensive study of the various phases, namely, segmentation, feature extraction and classification techniques required for an OCR system especially for ancient documents. It has been observed that there is a limited work is done for the recognition of ancient documents especially for Devanagari script. This article also presents future directions for the upcoming researchers in the field of ancient text recognition.

Prevalence of Covert Hepatic Encephalopathy in A Tertiary Care Centre

Among patients with Hepatic Encephalopathy, prevalence of Minimal HE varies between 30-50%. Identifying patients with MHE has been shown to improve with medications and delay development of Overt HE, however only limited clinicians screen for MHE in patients due to time consuming neuropsychological and neurophysiological tests. The Number Connection Test is an easy way to evaluate patients to diagnose MHE. The aim of this study is to find out the prevalence of covert hepatic encephalopathy. The descriptive cross-sectional study was done to find out the prevalence of covert hepatic encephalopathy among patients with chronic liver disease. To diagnose Covert HE which included MHE as well, NCT was used in Devanagari script. The prevalence of covert hepatic encephalopathy is found to be 56 (58.3%) at 90% confidence interval (58.23-58.37%). A total of 96 patients (71.9% male) were diagnosed as HE, with mean age of 49.6+11.8 years. The cause of CLD in 85 (88.5%) of these patients was alcohol, of which 76 (79.2%) consumed locally brewed alcohol. Of these 96 patients with HE, only 40 (41.7%) had overt HE. Among all these, maximum patients had MHE (37.5%). Our study showed that although the prevalence of minimal HE is quite high among cirrhotics, they are usually missed in clinical practice due to absence of symptoms. Active screening with easy-to-administer tests, like Number Connection tests, can help identify patients with minimal HE and hence treat them early.

A Novel Approach for Character Segmentation of Offline Handwritten Marathi Documents written in MODI Script

Abstract One of the most challenging module in any handwritten character recognition system is separating individual characters from the document. Better character recognition rate is highly influenced by how much accuracy, character segmentation phase, has achieved. As the input data set is contains documents written in MODI script, and since MODI script characters are written in cursive manner, obtaining individual characters from the text becomes extremely complicated. Moreover, there is no separation between two adjacent words. Although now-a-days, Marathi language uses Devnagari script, several years back MODI Script was used for writing documents in Marathi language. This work presented in this paper tackles segmentation of individual characters from ancient handwritten MODI Script documents. Vertical Projection Profile (VPP) method can segment characters from a given line accurately only when two adjacent characters are separated by a zero-pixel column. Since characters of one line in this script are written without lifting hand, output of VPP does not suffice. This paper presents a novel approach for isolating individual characters from the line obtained using authors’ previous research work which uses dual thresholding criterion to minimize the character segmentation error. The techniques used in this paper are straightforward and reasonably economical in terms of execution time efficiency. The results obtained are quite satisfactory.

A Novel Geometrical Scale and Rotation Independent Feature Extraction Technique for Multi-lingual Character Recognition

This paper presents a novel geometrical scale and rotation independent feature extraction (FE) technique for multi-lingual character recognition (CR). The performance of any CR techniques mainly depends on the robustness of the proposed FE methods. Currently, there are very few scale and rotation independent FE techniques present in the literature which successfully extract the robust features from characters with noise such as distortion and breaks in the characters. Many FE methods from the literature failed to distinguish the characters which look similar in their appearance. So, in this paper, we have proposed a novel scale and rotation independent geometrical shape FE technique which successfully recognized distorted, broken, and similarly looking characters. Aside from the proposed FE technique, we've used crossing count (CC) features. Finally, we have combined the proposed features with CC features to make as Feature Vector (FV) of the character to be recognized. The proposed CR technique is evaluated using publicly available media-lab license plate (LP), ISI_Bengali, and Chars74K benchmark data sets and achieved encouraging results. To further assess the performance of the proposed FE method, we've used a proprietary data set containing nearly 168000 multi-lingual characters from English, Devanagari, and Marathi scripts and achieved encouraging results. We have observed better classification rates for the proposed FE method using publicly available benchmark data sets as compared to few of the CR FE methods from the literature.

Classification of Handwritten Devanagari Number – An analysis of Pattern Recognition Tool using Neural Network and CNN

This paper majorly concerns the classification of handwritten numerals of Devanagari Script. The major contributions in this paper are 1) Development of a dataset for handwritten numerals similar to MNIST dataset, 2) Analysis of Pattern Recognitions tools based on NN and Convolution Neural Network, 3) Detailed discussion on the results by calculating the Precision, recall and F-measure values and compared with the other dataset available online. The present dataset includes 4,282 handwritten numerals of Devanagari which are collected from people of different ages. In the methodology developed in this paper, all the numerals are extracted from the image. After pre-processing, the images are resized to 30X30 which are later converted to vectors. These vectors with labels are the inputs for the classifiers. ANN classifier is designed by using PRTool and Deep Learning network is designed to make comparison with ANN. Data for training and testing splits into different ratios – 80:20, 70:30, 60:40 and 50:50. This research has achieved accuracy of more than 95%. The results of the dataset generated are compared with the dataset available online.

A scene perception system for visually impaired based on object detection and classification using CNN

In this paper we have developed a system for visually impaired people using OCR and machine learning. Optical Character Recognition is an automated data entry tool. To convert handwritten, typed or printed text into data that can be edited on a computer, OCR software is used. The paper documents are scanned on simple systems with an image scanner. Then, the OCR program looks at the image and compares letter shapes to stored letter images. OCR in English has evolved over the course of half a century to a point that we have established application that can seamlessly recognize English text. This may not be the case for Indian languages, as they are much more complex in structure and computation compared to English. Therefore, creating an OCR that can execute Indian languages as suitably as it does for English becomes a must. Devanagari is one of the Indian languages spoken by more than 70% of people in Maharashtra, so some attention should be given to studying ancient scripts and literature. The main goal is to develop a Devanagari character recognition system that can be implemented in the Devanagari script to recognize different characters, as well as some words.

Automatic Handwritten Devanagari Text Generation in Marathi Styles using Ant Miner Algorithm

The Devanagari scripts forms the backbone of the writing system of several Indian languages includes Hindi, Sanskrit and Marathi. With the increased demand, exploration and globalization of digital Devanagari documents, different printed and handwritten document recognition techniques have involved since last two decades. In literature many methods of Devanagari script recognition have been used but it is not able to attain the best results in recognition. Hence, in this paper is proposed Ant Miner Algorithm (AMA) for recognition and text generation of handwritten Devanagari Marathi Scripts. The proposed method recognition process is working with the four different stages such as pre-processing, segmentation, feature extraction and recognition with text generation. The first stage pre-processing is consists of skew correction, noise removal and binarization. The second stage is segmentation that contains the line segmentation, word segmentation and character segmentation. The third stage is feature extraction method it contains four methods such as Scale Invariant Feature Transform (SIFT), Linear Discriminant Analysis (LDA), Discrete Cosine Transform (DCT) and Local Binary Pattern (LBP). The final stage is recognition and text generation with attain with the help of AMA algorithm. It works based on the two phases such as training and testing phase. The proposed method is implemented in the python platform and it compared with the Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN). The performance of the proposed method is analysed with statistical measurements of accuracy, precision and recall.

Writer identification system for pre-segmented offline handwritten Devanagari characters using k-NN and SVM

A biometric identification system based on single and multiple modalities has been an evolving concept for solving criminal issues, security and privacy maintenance and for checking the authentication of an individual. The writer identification system is a type of biometric identification in which handwriting of an individual is taken as a biometric identifier. It is a system in which the writer can be identified based on his handwritten text. These systems employ machine learning and pattern recognition algorithms for the generation of a framework. In this paper, the authors have presented a novel system for the writer identification based upon the pre-segmented characters of Devanagari script and also presenting comprehensive state-of-the-art work. The experiment is performed on the corpus consisting of five copies of each character of Devanagari script written by 100 different writers, selected randomly at the public places and consisting of total 24,500 samples of Devanagari characters. Four feature extraction methodologies such as zoning, diagonal, transition and peak extent-based features and classification methods such as k-NN and linear SVM are used with identification accuracy of 91.53% when using zoning, transition and peak extent-based features with a linear SVM classifier.

Language Identification for Multilingual Sentiment Examination

Social media is most popular platform on which users can share their views, reviews and knowledge about various topics, news, products etc. Identifying sentiments or opinions of users is valuable for many e-commerce companies, Hotels, e-learning etc. This opinion analysis is useful for companies to improve their service and products. Due to increase in web users across globe, users happen to post their views freely over the internet. Many different languages are spoken across globe, supporting multilingual nature of social media makes analysis of such text difficult. Sentiment analysis can be conducted using videos, image, text, where text sentiment analysis is most popular form because of freely available contents in the form of blogs, reviews, comments etc. Because of development of social media platform, people can post comment in any language, creates the need for Multilingual sentiment analysis. Sentiment analysis task needs phases such as data collection, pre-processing, sentiment classification and polarity identification. The Multilingual nature needs Script Identification on the input text by labelling the different words used in text along with scripts used to denote them. Various languages used in the text are identified and the Hindi language text written in Romanized script is transliterated to Devanagari script. Text is then completely translated into English language and POS(Parts of Speech) tagging is performed on the obtained text. The aim and purpose of this study is to survey different techniques of multilingual sentiment analysis, and language identification of source text, where n-grams model outperforms all.