Abstract
This article discusses common approaches to the development of ANPR systems. The main idea of the article is the parallel use of several different classifiers for OCR and fusion of obtained data for improving the recognition accuracy.
Majority voting approach and fuzzy logic rules in license plate recognition process
2014
Closed access Metadata (CSL-JSON)
How this score is calculated
It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.