This chapter reviews salient advances in techniques for machine-printed character recognition. Section "Overview" provides a historical perspective (The description of the historical evolution of OCR is based upon the Wikipedia entry for this topic: http://en.wikipedia.org/wiki/Optical_character_recognition. The reader is referred to that page for a more detailed review) on how OCR techniques have evolved from the earliest stage (mechanical device) to special-purpose reading machines and to personal computer software. Section "Summary of the State-of-the-Art" summarizes the state of the art in machine-printed character recognition. Sections "Segmentation and Preprocessing", "Isolated Character Recognition", and "Word Recognition" describe core technologies including binarization, document image preprocessing, page segmentation, feature extraction, character classification, and language modeling that have been developed for modern character recognition systems. Section "Systems and Applications" introduces available machine-printed OCR systems and applications.
CITATION STYLE
Cao, H., & Natarajan, P. (2014). Machine-printed character recognition. In Handbook of Document Image Processing and Recognition (pp. 331–358). Springer London. https://doi.org/10.1007/978-0-85729-859-1_44
Mendeley helps you to discover research relevant for your work.