OCR stands for Optical Character Recognition, a software used to convert non-searchable PDF files into searchable mode. When the physical files are scanned to be uploaded into the document management system, they are initially in the form of an image basically wherein the text inside the same cannot be identified by DMS if a content search is performed.
However, the very purpose of implementing a document management system gets defeated if you fail to perform a content search and retrieve files based on the same. That is where the role of an OCR software comes into play. OCR is installed in your DMS as a plugin which converts every non-searchable pdf file i.e. basically scanned files, into a searchable format so that the text inside the file can be read by the DMS.
Let us take an example to understand the working of OCR better. For instance, you have scanned and uploaded a purchase order into DMS. Now without OCR, the software would fail to identify the text inside it. So when you run a content search with the name of the customer or the value of the order, it won’t retrieve the file as a result. However, once the OCR plugin is installed the same is displayed as a result.
However, it needs to be understood that no OCR software is entirely accurate. There are multiple OCR applications available in the market and the accuracy depends on which one you opt to integrate with your DMS. No guesses that for better accuracy, you would have to shell out a lot more than usual. However, companies nonetheless go ahead with the same because without a fully working content search module the ROI on implementing a document management system is never really recovered.
For handwritten text, a different technology is used which is known as ICR, Intelligent character recognition, the accuracy of which is much lower than that of the traditional OCR.