Abstract
In this era of growing automation, automatic character recognition has become need of the hour. Optical character recognition (OCR) techniques allow computers to recognize handwritten characters and change them in digital format or other formats which are understandable by computers. This automatic recognition requires feature extraction from character images. Feature extraction is a very important phase of character recognition. This paper discusses features based on shapes, skeletons, image moments, image transforms, critical points, etc. This paper also investigates different types of features used in literature works. A good feature set results in good recognition rates. Thus, it is important to have knowledge of different types of features and their properties. This paper benefits its readers by providing them insight of different types of features and helps them in identifying the appropriate feature set according to their application.
Highlights
Automatic character recognition is conversion of handwritten documents in computer editable format
Optical character recognition (OCR) techniques allow computers to recognize handwritten characters and change them in digital format or other formats which are understandable by computers
This paper investigates different types of features used in literature works
Summary
Automatic character recognition is conversion of handwritten documents in computer editable format. Automatic recognition of numerals and letters written on cheques and other documents can highly elevate the work capacity. In post offices, universities and colleges automatic form processing, and checking can reduce paper load and save environment. Apart from these benefits, automatic recognition system helps in restoring old degraded books. It is an aid for physically challenged person, as it can be used for synthetic speech generation. Online recognition systems work on real time information and extract features more accurately and than offline systems. Chinese handwritten character recognition are mainly based on CASIA-HWDB1.0 and 1.1 [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Research in Computer Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
