Optical Character Recognition

Abstract

Recognition of characters relates to emblematic identity with the image of character. Majority of the OCR systems input characters are first converted to digital form by an optical scanner. Every character is first located and segmented, and the resulting character image is fed into a pre- processor for noise reduction and normalization. Certain characteristics are the extracted from the character for classification. Numerous techniques exist for feature extraction each one having its own merits and de-merits. After classification and training the identified characters are grouped to reconstruct the original symbol strings, and various algorithms may then be applied to detect and correct errors.