Recognition of typewritten Gurmukhi characters
by Rajan Goyal; Rajesh Kumar Narula; Manish Kumar Jindal
International Journal of Computer Aided Engineering and Technology (IJCAET), Vol. 17, No. 3, 2022

Abstract: Today, extensive research has been done on data analysis and text recognition, currently numerous optical character recognition (OCR) frameworks are available by various researchers. Language scripting is considered as a challenging task due to the presence of degraded characters which affects the OCR performance. In Gurumukhi content, old reports are inaccessible because of its delicate condition. For the most part old archives get debased which hampers their lucidness. The utmost work is done by researchers on character recognition of Gurmukhi script dealing with handwritten and printed characters. The aim of this research work is to cover blind spot area of typewritten Gurmukhi script for recognition of character. To achieve this, features are extracted using projection profiles, zoning features, transition features, distance vector and neighbouring pixels and machine learning techniques like SVM (using linear and polynomial kernel) and k-NN (with value of k = 3, 5, 7 and 11) are applied to recognise the characters. It is found that SVM linear approach provides best result in our case.

Online publication date: Tue, 27-Sep-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Aided Engineering and Technology (IJCAET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com