OCR SDK Scalability

Language:
EN
Product-Line:
FlexiCapture Engine, FineReader Engine
Version:
9.x, 10, 11
Type:
Technology & Features, Scenarios/Tasks
Category:
Recognition, OCR: Speed & Quality
  • OCR tasks are very CPU intense and can use almost 100% of the available computing power of a machine.

    Note: 100 % System load will not last just for seconds, but for days/weeks or even months when you have enough pages ;-); Used for the screenshot, Quad core with hyper-threading, sample: Multi-Core Processing in FlexiCapture Engine
  • OCR processing speed is very important in real live applications and projects, but ultimately it is not that important how fast the processing/throughput on one CPU core is.
    Why? – Single Core machines do not exist any more - and CPU power has become rather cheap. The price difference between a 4-core or an 8-core server are becoming irrelevant.
  • Scalability 1.0” is about using multiple cores/CPUs on one machine. Here it is important how the OCR or data extraction engine scales up with different processes and threads, see Multi Core CPUs,
  • Scalability 2.0” is about processing in a network, - at the end that makes the real difference.
    Often this is not only a technical problem, but more or less tied to the business model of the technology provider.
This website uses cookies which enable you to see pages or use other functions of our websites. You can turn off such cookies in your browser’s settings. If you continue to use these pages, you consent to the use of cookies.