AccuSoft ImageGear Professional
Recognition
Incorporating a range of recognition functionality via the ScanSoft® OmniPage® Capture SDK, the ImageGear OCR component is more than just an OCR toolkit, providing unsurpassed recognition accuracy for almost any document type.
Barcode
ImageGear barcode functionality provides an API for reading barcodes in
all supported image formats. In imaging, barcodes provide a means
of quickly obtaining information for use in indexing data or for use by
an application.
The ImageGear barcode support provides the ability to search for a
barcode on a page, recognize its symbology and recognize the data
within. Images with barcodes can be acquired through scanning or using
ImageGear operations to read previously saved scanned images from
memory.
Highlights include the following:
- Selection of symbologies for recognition
- Setting barcode properties (i.e., width, height, orientation, image quality, checksum verification, spot-filter use, effort of searching and search order
- Setting barcode regions relative to the image's rectangular ROI
- Reading barcodes from the region set
- Getting distinct barcode text and other information found through a previous reading of barcodes
- Removing barcode region and freeing-up memory allocated for the region
- CODABAR
- Code 128
- Code 39 (a.k.a. 3 of 9)
- EAN 8/13
- EAN/UPC with 2 & 5 digit supplement
- ITF (2 of 5 interleaved)
- PostNet
- UCC Code 128
- UPC-A
- UPC-E 6 digit
- PDF417 (2D)
OCR - Optical Character Recognitionnn
The ImageGear OCR component enables developers to build recognition applications for Windows systems. When utilized in an application, it will acquire a page image as input and produce recognized text in a variety of output formats.
ImageGear OCR provides a new scalable voting architecture that provides developers with two pre-made voting interfaces along with direct access to three leading OCR engines, enabling the best possible results for their applications:
MOR OCR Engine
- Supports 114 languages s
- Supports a maximum of 500 zones on one image
- Supports Omnifont, Draftdot24 and OCR-A filling methods
- Supports character training to achieve improved accuracy
- Provides three page-level accuracy and speed trade-off settings (Accurate, Balanced and Fast)
- Provides Checking Subsystem-based correction
- The fastest of the selectable OCR engines
- Support for 12 languages
- Supports a maximum of 64 zones on one image
- Supports Omnifont, Draftdot9 and Draftdot24 filling methods
- Provides two page-level accuracy and speed trade-off settings (combined Accurate/Balanced and Fast)
- Provides Checking Subsystem-based correction
- Optimized for speed
- Support for 54 languages
- Supports a maximum of 2,500 zones on one image
- Supports Omnifont filling methods
- Supports character training to achieve improved accuracy
To further improve output accuracy, quality format retention is available. This separates text, graphics, tables and columns to provide greater fidelity.
ICR - Intelligent Character Recognition
Developers have a choice of integrating two ICR (handprint OCR) recognition modules, including a numbers only module and an alphanumeric handprint recognition module. The numeric-only module is designed for a restricted character set, and can recognize the following: Digits (0-9), Plus sign (+), Minus sign (-), Period or full-stop (.), Comma (,).
Typical recognition time is 280-310 characters-per-second (measured on a computer with 1.5 GHz Pentium processor, 256 MB RAM, running Windows 2000).
The Alphanumeric ICR module recognizes hand-printed characters (both upper- and lower-case) of nearly 100 languages, 15 with dictionary support, including:
- Catalan
- Czech
- Danish
- Dutch
- English
- Finnish
- French
- German
- Hungarian
- Italian
- Norwegian
- Polish
- Portuguese
- Spanish
- Swedish
OMR - Optical Mark Recognition
The OMR recognition module is used for recognizing optical marks. Typical areas of application include questionnaires, educational tests, and in reporting or ordering sheets—where the documents being processed are form-like and filled in by respondents.
The frame can be a rectangle, hexagon, circle or ellipse and can be filled in by any method (x, tick, hatching, horizontal or vertical lines, etc.). The frame may be visible or invisible (scanner dropout) in the image sent for recognition. Recognition accuracy is 99.95 % and the average recognition time is 0.005 seconds per checkbox zone (measured on a computer with 166 MHz Pentium Processor & 16 MB RAM).
