Tags Used in Articles on User Friendly Consulting

MuWave OCR Unlimited

  • UFC's MuWave brand logo

    MuWave Classify / Extract QSX

    MuWave Classify / Extract is a Quillix Server Extension module (QSX) which provides automatic classification and extraction functions from a variety of different document types. This solution works by first classifying the document and then once it has determined the document type it extracts critical data from within the document. The system uses three different methods to locate data from a document including a text string, regular expression, or barcode.  Search zones can be specified to limit the extraction of data to a particular region of a document.

    Key Features of MuWave Classify / Extract:

    • Automatically determine the document type such that the extraction rules can be applied to each of the different document classes. 
    • User interface provided to create extraction rules using these methods
      • Search for a plain text string,
      • Search using a regular expression (REGEX),
      • Search using the identification of a barcode located within the document
      • Combined search using a text string, REGEX, or barcode value but applied to a search zone within the document.

    Benefits of MuWave Classify / Extract:

    • Eliminates the need for the use of much more costly document capture software when only a few index values are required to be extracted from within a document.
    • Eliminates the need to purchase a per-page or total page count licensed OCR licensed form processing solution.
    • Eliminates the need to add another document capture software application when a customer is already using Quillix Capture. 
    • Leverages the intuitive and easy to use indexing screen already familiar to Quillix Web users. 
    • Reduces administrative expense because the solution simply plugs into the Quillix capture platform without the requirement to install any other software. 

    Optional Features:

    Intelligent Character Recognition (ICR) is optional should a need arise to extract handwriting information from a particular zone. The zone is identified using one of the available search techniques for location. This means that the system searches for something like a heading or "labelled field" information and then extracts the handwriting based upon the specified location relative to this field.

    Did You Know:

    • MuWave Classify / Extract is a software component that plugs into the Quillix Web Document Capture application.  This document capture software application has been chosen by many large firms including global energy services company Halliburton.  Read the case study about how Halliburton is using Quillix as their global document capture platform. 
    • UFC offers an unlimited OCR engine which was designed from the beginning to work with this product. This OCR software application eliminate the need for per-page or total page count licenses of the OCR engine and provides extremely rapid OCR production compared to competitive products.  MuWave Unlimited OCR also provides an extremely scalable OCR platform. A full 8 cores of OCR processing power are provided in the standard base level configuration.  Imagine paying for an 8 CPU license with a competitve OCR application, and page counts to boot.  Find out more about MuWave OCR Unlimited
  • MuWave OCR Unlimited QSX

    MuWave OCR QSX Data Sheet

    MuWave® OCR Unlimited is Quillix™ server extension that provides an efficient means of generating textual information from images. It produces both text and searchable PDF versions from images or PDFs. In addition, a built-in Visual Basic scripting interface allows advanced operations to be completed, such as storing the output files to a network storage device or inserting text into a database.



    • Accepts any image file that Quillix Server supports. This includes TIFF, JPEG, BMP, TARGA, PNG, and PDF files (image only or image and text).
    • Works within any Quillix document or batch level workflow.
    • Unlimited page processing with multithreaded operation up to the licensed limit of cores.
    • Provides unlimited page processing across multiple Quillix servers.
    • No “per click” OCR page costs.
    • Accurate text recognition >99% accuracy for 300 dpi typed text images.
    • Automatic line removal for form-based documents.
    • Advanced enhancement of grayscale and fuzzy images for maximum text extraction.
    • Native PDF processing using Adobe’s own tools.
    • PDF output files are not rendered versions—they are the original files with a text layer added.
    • Option to bypass PDFs that are already searchable for maximum speed.
    • When used with other MuWave products such as MuWave Rendition QSX, capable of processing any file type including Word, Excel, PowerPoint, etc.
    • Custom logging option for generating messages in the Quillix audit log.
    • Built-in Visual Basic scripting for performing advanced operations such as calling custom COM objects.
    • Integration with MuWave Reports and other MuWave modules for a comprehensive capture solution.