2.80:OCR Synthesis (Concept): Difference between revisions

Revision as of 16:15, 11 February 2020

The Synthesis functionality is Grooper's unique method of reprocessing raw results from the OCR engine.

Revision as of 13:51, 30 December 2019 view source Configadmin (talk \| contribs) Interface administrators, Administrators 1,305 edits Created page with "The Synthesis functionality is Grooper's unique method of reprocessing results from the OCR engine. Raw character data is converted into a text flow. Words ar..."		Revision as of 16:15, 11 February 2020 view source Dgreenwood (talk \| contribs) Bureaucrats, Administrators 16,516 edits No edit summary Newer edit →
Line 1:		Line 1:
	The Synthesis functionality is Grooper's unique method of reprocessing results from the [[OCR Engine\|OCR engine]]. Raw character data is converted into a text flow. Words are simply groups of characters separated by white space as far as text data is concerned. While the individual character confidence is important, if the average confidence of a group of characters is low, it's likely that group of characters didn't get OCR'd as what is on the page. Synthesis allows users to group characters into segments separated by whitespace and reprocess them if their average character confidence falls below a certain threshold to ensure higher accuracy.		The Synthesis functionality is Grooper's unique method of reprocessing raw results from the [[OCR Engine\|OCR engine]].