Published:
Scanning office documents now goes beyond saving digital images. OCR recognises text in scans, enabling files to function as searchable textual versions of their paper originals.
OCR and document processing
OCR turns office equipment into document processing tools. Scanned documents can be searched and edited, making data easier to use.
OCR can be implemented through a computer application that recognises text in previously scanned images, or through equipment with built-in OCR that recognises text during scanning.
How OCR software works
Optical Character Recognition converts characters in images into computer-readable text. It makes a scanner useful for digitising written documents as well as capturing images.
Converting a scan or photograph to text involves several steps:
- Loading the image and identifying blank areas, graphics and text regions.
- Recognising text using methods such as feature analysis and comparison with stored character patterns.
- Creating and saving text: recognised characters are combined into words using dictionary references, then assembled into a document.
Separate OCR software versus built-in recognition
Before buying a scanner, consider whether built-in OCR or a separate application better suits the office and user requirements. Both have advantages and limitations.
Built-in recognition offers basic OCR conveniently and at low cost, with a short document-processing workflow that can be initiated from the device controls.
Separate OCR software generally costs more but provides greater functionality and scope for expansion, supporting specialised office requirements.