A Survey on Techniques of Separation of Machine Printed Text and Handwritten Text
Ranjeet Srivastva1, Aditya Raj2, Tushar Patnaik3, Bhupendra Kumar4
1Ranjeet Srivastva, M. Tech, Department of IT, C DAC, Noida, India.
2Aditya Raj, M. Tech (CSE), Department of CSE, C DAC, Noida, India.
3Tushar Patnaik, Sr. Lecturer, Sr. Project Engineer, Department of CSE, C DAC, Noida, India.
4Bhupendra Kumar, Sr. Technical Officer, Department of CSE, C DAC, Noida, India.
Manuscript received on January 20, 2013. | Revised Manuscript received on February 14, 2013. | Manuscript published on February 28, 2013. | PP: 552-555 | Volume-2 Issue-3, February 2013. | Retrieval Number: C1192022313/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: 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 to process it. This separation will definitely increase the performance and overall system quality. The paper discusses some observations about characteristics of these two types of texts and various techniques of separation of machine printed and handwritten text into three categories (Structural and statistical features, Gradient features and Geometric features) based on feature extraction method.
Keywords: Feature Extraction, Handwritten Text, Machine Printed Text, OCR.