TY  - JOUR
TI  - Optical Character Recognition - A Review
AU  - Dr. S.Vijayarani
AU  -  M. Geetha
JO  - International Journal of Scientific Research in Computer Science, Engineering and Information Technology
PB  - Technoscience Academy
DA  - 2017/10/31
PY  - 2017
DO  - https://doi.org/10.32628/IJSRCSEIT
UR  - https://ijsrcseit.com/CSEIT1725216
VL  - 2
IS  - 5
SP  - 942	
EP  - 947
AB  - Optical Character Recognition (OCR) is the transformation of digital document images into editable text format. Nowadays, most of us downloading the digital documents and e-books from an internet. Normally, most of the downloaded documents are available in the form of images, so it is impossible to edit or to perform search process for extracting any information from these digital documents. Optical Character Recognition is a process of detecting and recognizing the characters from the document images. Documents are converted into digital form with the help of scanners and mobile phones. Scanners scan the documents, whereas mobile phones takes the snapshots of the documents. OCR technique helps to convert handwritten or printed document images into editable form and then we can perform document editing and searching process. The main disadvantage of OCR tool is the accuracy, i.e. it unable to translate the document image accurately into editable form. The OCR does not convert some of the characters, numbers and special symbols in the document images properly. Therefore, there is a need for development of accurate OCR techniques, which can able to perform search and edit processes successfully. This paper studies the fundamental concepts of OCR, significant steps, and their related works.