Separation of Machine Printed and Handwritten Text for Hindi Documents
Ranjeet Srivastava, Ravi Kumar Tewari, Shashi Kant · 2015
In many documents such as admission form, bank cheques, memorandums, letters and application forms machine printed and handwritten characters are mixed. Since the algorithms for recognition of machine-printed texts and handwritten texts are different, it is necessary to distinguish between these two types of texts before giving it to respective OCR systems. This separation will definitely increase the performance and overall system quality. In this paper, an approach for separation of machine printed and handwritten text in Hindi documents has been proposed. Statistical and structural features are used to distinguish between these two texts. This separation is performed on word level and achieved accuracy of the system is about 94.1%.