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.

Research Survey on Skew Detection of Devanagari Script

Abstract: Skew detection is one of the important part of any document image processing or character recognition system. The successful skew detection and correction may leads to success of document image processing or character recognition system. The skew is may be of scanned document image or of handwritten data. This paper gives the survey of various skew detection techniques used for Devanagari script as well as other scripts. The methods which are used mostly for skew detection like Hough transform, Fourier transform, projection profile, principle component analysis, nearest-neighbor clustering and cross-correlation are described in this paper.

A Research Survey on Sanskrit Offline Handwritten Character Recognition

Abstract: Sanskrit (Devanagari), an alphabetic script, is used by over 500 million people all over the world. Recognition of Sanskrit (Devanagari) handwritten scripts is complicated compared to other language scripts. However, many researchers have provided real-time solutions for offline Sanskrit character recognition also. Offline Sanskrit handwritten documents recognition still offers many motivating challenges to researchers. Current research offers many solutions on Sanskrit (Devanagari) handwritten documents recognition even then reasonable accuracy and performance has not been achieved. This paper analyses the various approaches and challenges concerning offline Sanskrit (Devanagari) handwritten character recognition.

Printed and Handwritten Character &Number Recognition of Devanagari Script using SVM and KNN

Abstract: Recognition of Devanagari scripts is challenging problems. In Optical Character Recognition [OCR], a character or symbol to be recognized can be machine printed or handwritten characters/numerals. There are several approaches that deal with problem of recognition of numerals/character. In this paper we have compared SVM and KNN on handwritten as well as on printed character and numerical database for this we have created four different database.

A Survey on Devanagari Character Recognition

Abstract: Development of optical character recognition (OCR) algorithm for printed and handwritten characters is a challenging area for research. Plentiful research on OCR techniques for scripts such as Roman, Japanese, Korean, and Chinese has already been carried out. OCR research activities related to Indian script is limited. Devanagari script is used by about 500 million people in India. Remarkable research has been done in the last few years for Devanagari script. In this paper, a survey of the various research efforts done by various groups of researchers for the development of printed as well as handwritten Devanagari character recognition system is presented. Comparison of various methods in terms of feature extraction techniques, classifiers, datasets, and accuracy values is also described.

Handwritten devanagari (marathi) character recognition using svm and mlp

Abstract: Many researchers are working to automate the process of reading, understanding and interpretation of handwritten character. In this paper, we present the new machine learning algorithm for Handwritten Devanagari (Marathi) characters recognition. Offline handwritten character recognition is an important area of Document Analysis and Recognition (DAR). DAR is a mechanism in which the document images are processed to obtain features and its recognition. Each character is stored as an image. The histogram oriented gradient features are extracted. The algorithm is designed to select the extracted features. There is 25% reduction in the feature set. These features are classified using SVM and the obtained average recognition accuracy is on testing is 95.83% and on cross validation is 95.82%. MLP classifiers accuracy is 95.45% on testing and on cross validation is 95.32 % with TanhAxon as Transfer function.