The authors present a methodology for automatically assessing the accuracy of such decompositions, and demonstrate its use in evaluating six OCR systems.

Alternatively, the user can let the OCR system automatically identify text regions and their order. The system finds columns of text and, if they are not part ...

Alternatively, the user can let the OCR system automatically identify text regions and their order. The system finds columns of text and, if they are not part ...

Commercial OCR systems allow the user to demarcate the text regions on a page image by drawing boundaries around them. The order of these regions, or zones, is ...

Original language, English. Pages (from-to), 86-90. Number of pages, 5. Journal, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Apr 6, 2015 · It consists of a few experiments primarily linked to text line segmentation. Al-though they are mutually independent, the re-sults obtained are ...

We present a methodology for automatically assessing the accuracy of such decompositions, and demonstrate its use in evaluating six OCR systems. References. [1].

Automated evaluation of OCR zoning. Abstract: Many current optical character recognition (OCR) systems attempt to decompose printed pages into a set of zones ...

Automated evaluation of OCR zoning. IEEE Transactions on. Pattern Analysis and Machine Intelligence, Vol. 17, 1995, pp. 86-90. 12. Krishnamoorthy M, Nagy M ...

Automated evaluation of OCR zoning. Automated evaluation of OCR zoning. by George Nagy. 1995, IEEE Transactions on Pattern Analysis and Machine Intelligence.