Research Article
Durgesh Dixit · Dr. Saroj Hiranwal
Journal
International Journal of Digital Applications and Contemporary Research (IJDACR)
ISSN
2319-4863
Volume / Issue
Vol.9 · Issue 3
Published
October 2020
Access
Open Access
Licence
CC BY-NC-SA 4.0
The massive digitization of paper documents has revealed the need for highly efficient writing recognition systems. Digitizing these documents allows you to perform operations such as keyword searches or retrieval of high-level information (title, author, addresses, and.). However the recognition of writing and in particular the handwriting are not yet at the level of human performance on complex documents, which restricts or harms some applications. The selection of features is an important step in any pattern recognition system. This selection of features is considered a combinatorial optimization problem and made the object of research in many disciplines. The main objective of the selection of features is to reduce the number of them by eliminating redundant and irrelevant features recognition system. The second objective of this feature selection is also to maintain and/or improve the performance of the classifier used by the recognition system. In this paper, support vector machine (SVM) based approach is proposed to solve this type of problem in the recognition of character. Hindi character recognition system which is capable of recognizing Hindi character with the help of morphological operation, edge detection, HOG feature extraction and Bayesian optimized support vector machine (SVM) based classifier
Durgesh Dixit, Dr. Saroj Hiranwal (2020). Hindi Character Recognition using HOG and Bayesian Optimized SVM Classifier. International Journal of Digital Applications and Contemporary Research (IJDACR), Vol.9, Issue 3. ISSN: 2319-4863.
Full references are available in the PDF version of this paper.
Download Full Paper (PDF) →Share This Paper
Call for Submissions
IJDACR accepts submissions on a rolling basis. Authors are advised to consult the preparation guidelines and scope documentation prior to submission.
Submissions are subject to editorial screening and peer review. Submission does not guarantee acceptance.