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.

Digitization of handwritten devanagari text using CNN transfer learning – A better customer service support

Abstract: Devanagari script is one of the bases of various language scripts in India. With the growth of computing and technology, manual systems are replaced by automated one. The purpose of this research is to automate the existing manual system for digitization of Devanagari script with the use of an automated approach so that it saves time, antique data. The prescriptions given by the expert doctors and the treatments which are present in ancient Vedic literature are useful for handling patients with serious diseases. Digitization helps in easy access, manipulation, and longer storage of this data. Unlike Western languages such as English, Devanagari, is a famous script in India which does not have formal digitization tools. This work employs the best suited techniques that are useful to enhance the recognition rate and configures a Convolutional Neural Network (CNN) for effective Devanagari handwritten text recognition (DHTR). This approach uses Devanagari handwritten character dataset (DHCD) which is a vigorous open dataset with 46 classes of Devanagari characters and each of this class has two thousand different images. After recognition, conflict resolution is subtle for effective recognition therefore, this approach provides an arrangement to the user to handle the conflicts. This approach obtains promising results in terms of accuracy and training time.

Segmentation of Devanagari Handwritten Characters

Abstract: The world is fast moving towards digitalization. In the age of super-fast computational capabilities, everything has to be made digitalized so as to make the computer understand and thereby process the given information. Optical character recognition is a method by which the computer is made to learn, understand and interpret the languages used and written by the human beings. It provides us a whole new way by which computer can interact with human beings, in their own languages. Hence OCR has been a topic of interest for researchers all around the globe in the past decade and research paper involving OCR is increasing day by day. It is seen that efficient algorithms have increased the speed and accuracy of character segmentation and recognition. A substantial amount of work has been done on foreign languages such as English , Chinese etc. but very few paper are there for Indian languages baring a few for Hindi and Bengali. Hence our research work was directed towards development of a novel algorithm for Devanagari character segmentation for Hindi. Hindi is one of the eighteen languages recognized by the Indian constituency. It is also one of the oldest languages and is spoken by millions of people in India. Segmentation and Recognition of this particular language is difficult because of the presence of complex connected characters and presence of shirorekha. A novel approach has been proposed for the segmentation of the connected character. General Terms Pattern recognition, image segmentation.

A Novel Method to Segment Online Gurmukhi Script

Abstract: Segmentation of handwritten script in general and Gurmukhi Script in particular is a critical task due to the type of shapes of character and large variation in writing style of different users. The data captured for online Gurmukhi Script consists of x,y coordinates of pen position on the tablet, pressure of the pen on the tablet, time of each point and pen down status of the pen. A novel method to segment the Gurmukhi script based on pressure, pen down status and time together is presented in the paper. In case of some characters getting over segmented due to the shape of character and user’s style of writing, a method to merge the substrokes is presented. The proposed algorithms have been applied on a set of 2150 words and have given very good results.

A Deep Learning Approach for Optical Character Recognition of Handwritten Devanagari Script

Abstract: Handwritten Character Recognition is one of the most challenging and demanding area of interest for researchers in domains of pattern recognition and image processing. Many researchers have worked with recognition of characters of different languages but there is comparatively less work carried for Devanagari Script. In past few years, however the work carried out in this direction is increasing to a great extent. Handwritten Devanagari Character Recognition is more challenging in comparison to the recognition of the Roman characters. The complexity is mostly due to the presence of a header line known as shirorekha that connects the Devanagari characters to form a word. The presence of this header line makes the segmentation process of characters more difficult. There is uniqueness to the handwriting styles of every individual which adds to the complexity. In this paper, we propose development of Convolutional Neural Network (CNN) based Optical Character Recognition system (OCR) for Handwritten Devanagari Script which is observed to recognize the characters accurately.