Image Recognition Module – OCR Engine

Combining optical character recognition (OCR), optical mark recognition (OMR), barcode recognition and handwriting recognition (ICR) – The Esker Image Recognition Module extracts data from the image of any business document entering as a fax or a scanned document. The Esker Image Recognition Module increases efficiency and reduces errors by eliminating manual data entry tasks associated with incoming fax or image documents.

How it works

Features

  • Extracts data from inbound fax and image documents using optical character recognition (OCR), optical mark recognition (OMR), barcode recognition (1D and 2D) and handwriting recognition (ICR)
  • Extracts data from inbound fax and image documents for use with other applications and for creating new business documents
  • Extracts routing information from inbound fax and image documents, and automatically delivers the documents to the appropriate destinations
  • 2 Pre-Made voting OCR (machine print) recognition modules
  • Access to 3 individual OCR engines for application optimization
  • OCR-A, OCR-B, E-13B (MICR)
    • OCR A
      OCR B

      OCR-A/OCR-B Bar Codes

      E-13B (MICR)

  • 2 ICR (handprint) recognition modules
  • OMR (Checkbox)
  • Barcode recognition (1D and 2D)
  •  

Definitions

OCR:

Optical Character Recognition. The process of extracting words (and possibly layout and formatting information) from an image containing

OMR:

Optical Mark Recognition. Technically Optical Mark Recognition is the process used by an Optical Mark Reader to detect marks on a form being scanned. The term can also be used when referring simply to an Optical Mark Reader (see above).

Barcode:

A code representing characters by sets of parallel bars of varying thickness and separation that are read optically by transverse scanning .

ICR:

Intelligent Character Recognition. ICR is the computer translation of hand printed and written characters.

Double voting:

Technology that enables the parallel use of OCR engine plus a voting system. Alternatively, either one of the OCR engines may be individually applied on a field level basis to increase recognition accuracy.

Multi-Threading for multi processor architecture:

This technology features multiple number of threads per operation for optimal throughput on multicore CPUs for applications that deals with large number of images.