What is the difference between ICR and OCR technologies?
Very commonly, when people talk about the recognition technologies ICR, OCR, OMR, IWR, bar code and others that are combinations of the first four, everything gets thrown under the OCR umbrella. OCR is the most prevalent of all the technologies. It stands for “optical character recognition” and is the reading of machine-printed text on a document and the conversion of the text into a digital format.
ICR stands for “intelligent character recognition” and is the reading of hand-printed text on forms. The difference between hand printing and regular handwriting is that hand printing is constrained. Each character is separable from its neighbors, and ideally the text is mono-spaced on a unified baseline.
There are technologies for reading handwriting -- IWR, CAR, LAR -- but they are always tied to some additional lookup data. OMR, meanwhile, is the reading of bubbles and check marks. And bar code technology enables the reading of one-dimensional and two-dimensional bar codes on documents.
These various technologies also can be combined to create more advanced document recognition processes such as DataCapture, which involves storing field-data pairs in a structured or semi-structured form. You often can assume that when someone talks about OCR, they’re really speaking about the whole lot -- which very simply covers the entire process of converting paper-based information into digital content.
This was first published in May 2010