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.

Zernike Moment Feature Extraction for Handwritten Devanagari (Marathi) Compound Character Recognition

Abstract: Compound character recognition of Devanagari script is one of the challenging tasks since the characters are complex in structure and can be modified by writing combination of two or more characters. These compound characters occurs 12 to 15% in the Devanagari Script. The moment based techniques are being successfully applied to several image processing problems and represents a fundamental tool to generate feature descriptors where the Zernike moment technique has a rotation invariance property which found to be desirable for handwritten character recognition. This paper discusses extraction of features from handwritten compound characters using Zernike moment feature descriptor and proposes SVM and k-NN based classification system. The proposed classification system preprocess and normalize the 27000 handwritten character images into 30x30 pixels images and divides them into zones. The pre-classification produces three classes depending on presence or absence of vertical bar. Further Zernike moment feature extraction is performed on each zone. The overall recognition rate of proposed system using SVM and k-NN classifier is upto 98.37%, and 95.82% respectively.

Creation of data resources and design of an evaluation test bed for Devanagari script recognition

Abstract: The Indian subcontinent has a large number of languages, dialects, and scripts with the Devanagari script being the primary and most widely used of all the scripts. To date, much of the Devanagari optical character recognition (OCR) research has been restricted to a handful of groups. So, techniques have not yet been widely disseminated or evaluated independently and automated evaluation tools are currently not available for lack of a standard representation of ground-truth and result data. A key reason for the absence of sustained research efforts in off-line Devanagari OCR appears to be the paucity of data resources. Ground truthed data for words and characters, on-line dictionaries, corpora of text documents and reliable, standardized statistical analyses and evaluation tools are currently lacking. So, the creation of such data resources will undoubtedly provide a much needed fillip to researchers working on Devanagari OCR. This paper describes a National Science Foundation sponsored project under the International Digital Libraries program to create data resources that will facilitate development of Devanagari OCR technology and provide a standardized test bed and evaluation tools for Devanagari script recognition.

A fuzzy based classification scheme for unconstrained handwritten Devanagari character recognition

Abstract: The large data set and similar structural features of the characters in Devanagari script demand a highly efficient classification and recognition system. This paper presents a novel approach for the recognition of unconstrained handwritten Devanagari characters. The system is based on multi-stage classification scheme. The classification stages categorize the characters into smaller groups. The classification is done using two stages, first stage is based on fuzzy inference system and second stage is based on structural parameters. The fuzzy system improves the classification over crisp classification. The classified characters are passed to the feature extraction stage. The final stage implements feed forward neural network for character recognition. The recognition accuracy achieved by the proposed method is 96.95%.

Deep Learning Network Architecture based Kannada Handwritten Character Recognition

Abstract: In this work, a novel model for recognition of handwritten Kannada characters using transfer learning from Devanagari handwritten recognition system is presented. The objective is to use the knowledge of large data corpus of Devanagari recognition system as training data to perform the recognition of handwritten Kannada characters that has a smaller data corpus. The transfer of knowledge for recognition is carried out using deep learning network architecture to VGG19 NET. VGG19 NET is defined of five blocks of hidden layers, two dense fully connected layers and an output layer. Each block (except block1) consists of four convolution layers along with a max pooling layer. In proposed classification framework, Devanagari character set consists of totally 92000 images with 46 classes and Kannada character set is built with 81654 for training and 9401 for testing, for about 188 classes with each class comprising of 200–500 sample image. A total of 1,23,654 data samples is employed for training with VGG19 NET. For experimentation 9401 samples of about 188 classes built of about 40–100 samples in each classes is used and for which accuracy close to 90% is achieved. Validated accuracy after evaluation in 10 epochs with VGG19 NET, it has recorded an accuracy of 73.51% with a loss of 16.18%.

Relative positioning of stroke-based clustering: a new approach to online handwritten devanagari character recognition

Abstract: In this paper, we propose a new scheme for Devanagari natural handwritten character recognition. It is primarily based on spatial similarity-based stroke clustering. A feature of a stroke consists of a string of pen-tip positions and directions at every pen-tip position along the trajectory. It uses the dynamic time warping algorithm to align handwritten strokes with stored stroke templates and determine their similarity. Experiments are carried out with the help of 25 native writers and a recognition rate of approximately 95% is achieved. Our recognizer is robust to a large range of writing style and handles variation in the number of strokes, their order, shapes and sizes and similarities among classes.