IEEnews › IEEnews Windows, iPhone, Android, Gadget, Mac, How to Forum › How To Fix Errors Windows, iOS, Android › How to do Ocr of scanned texts, free of charge
- Nov 15, 2017 at 12:34 pm #21569
Optical Character Recognition (Ocr) programs allow you to convert them in text format after scanning documents, as if they were written through a word processor. This category of software now offers amazing results but remains commercial and non-economic packages.
In the freeware and open source world there are two projects that even though they do not have the rich features available in commercial solutions, offer very valuable results, as long as scanning quality is good (at least 300dpi but also greater resolutions if the document has very small characters ) and that you are willing to indicate the structure of the document manually if this is complex (so for documents that have text over multiple columns, images, tables, and so on).
FreeOCR is a project that employs the open source Tesseract engine that was originally developed by HP and then acquired by Google. The program, in addition to being able to analyze Tiff images, can process files directly into Pdf form.
FreeOCR can process documents in many languages. Basic offers Italian, English, Danish, German, French, Spanish, Polish, Swedish, Norwegian, Dutch and Finnish.
The program recognizes only the text: any formatting of the original document will be lost even if we use the export button to Word. Also, it does not support text placed in multiple columns: in these cases, you must manually point to parsing a column at a time.
You must be logged in to reply to this topic.