Recognition of typewritten Gurmukhi characters
Rajan Goyal, Rajesh Kumar Narula, Manish Kumar Jindal · International Journal of Computer Aided Engineering and Technology · 2022
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.