OCR, the abbreviation of Optical Character Recognition, is the conversion of image text into machine-encoded text, which is done by analyzing and matching through the image processing system. Scanning at 300 dpi (dots per inch) is not officially a standard for OCR, but it is considered the gold standard.
Most leading OCR software companies recommend scanning at a minimum resolution of 300 dots per inch for effective data extraction. As we’ve learnt from our previous article ‘What exactly is DPI ?’, scanning at 300 dpi means that for every square inch of paper, the scanner is capturing 300 dots horizontally and 300 dots vertically or 90,000 total dots (300 X 300 = 90,000 dots per square inch). If you use a 200 dpi setting instead of 300 dpi, you’ll only see 40,000 dots per square inch as opposed to 90,000. That’s a significant difference when you think about it.
So it’s easy for us to find out that, higher resolution scanning results to improved OCR accuracy. Since OCR is a technology where a computer is making a decision about a scanned character, having more dots per inch allows the computer a higher level of accuracy because it has more data to make the correct decision on the character.