Character extraction in EnginesPool is slow

  • Last Post 19 February 2020
lx11020219 posted this 20 January 2020

In the sample EnginesPool, extracting characters after OCR is slow.

Normally, OCR sample RecognizedTextProcessing is fast, so we want to have the same level of speed.

How can I solve it?


■Target file



■Comparison of processing time

 RecognizedTextProcessing → Avg0.18s


 EnginesPool → Avg15.2s


■Character extraction method

 Implemented in EnginesPool using "calculateStatisticsForLayout" of RecognizedTextProcessing


The source ZIP file could not be uploaded...

lx11020219 posted this 19 February 2020

Someone can explain how to improve the phenomenon that text extraction becomes slow when using EnginesPool because the support of ABBYY Japan isn't useful.
help me.