OCR (Optical Character Recognition) is the translation of an image of some text into a character representation (ASCII, Unicode). Use this text for questions related to conversion of image based text to a representation more efficient or usable on Ebooks

OCR means Optical Character Recognition and concerns issues related to the translation of an image of a typed, handwritten or printed text into a structure including a character by character (or symbol by symbol) representation of the text. The result may of may not include further information regarding the spatial organization of the text in the original image, and it may or may not include the original image together with the textual representation.

OCR may be coupled with the scanning of an original document to generate the image of the text, or it may be applied to an already scanned image represented, usually, in one of the standard formats for images. Hence it is distinct from scanning, which may also concern pictures and photographs.

For a complete presentation, see Wikipedia article on Optical character recognition.

history | excerpt history