Recogniform Workgroup Reader is the natural evolution of Recogniform Desktop Reader. The main difference is the possibility to operate with a ditributed architecture, instead of a single station.
Recogniform Workgroup Reader is made of five different applications:
Configuration can be set according to your needs: if the correction needs more stations, for example, you can install additional correction stations, as if you have more scanners you can speed-up forms acquisition installing more input stations.
Licensing allows to install an UNLIMITED number of INPUT, CORRECTION and OUTPUT stations, without paying any extra charge.
The communication between stations and server is TCP/IP based. In this way the Workgroup is suitable and ready for internet use, allowing you to place the stations in different locations. One of the many applications is the opportunity to have many operators working at home. At the same time, You could also acquire the input forms with no need to move them phisically from the place they are kept.
Fields of application
Thanks to its flexibility, Recogniform Reader is suitable for an wide range of possibilities. Here some:
Paper tests Optical Recognition
University Tests Recognition
Loyalty Card request forms
Registration Cards data catpure
Customer satisfaction Forms Recognition
Job Application Forms Recognition
Order forms data capture
Production Monitoring Forms recognition
Reports and manteinance forms data capture
FREE FORM Recognition
Semi-structured forms data capture
Not structured forms data capture
Using the state-of-art technologies, Recogniform Reader recognizes all kind of data, thanks to Recogniform recognition engines:
The OMR technology allows user to read the check boxes, that is the sign affixed in predefined spaces. The power of this engine, compared to similar products, is the advantage of working with two operative parameters, evaluating the quantity of existing ink and the size of the sign in the box.
With ICR system it's possible to recognize manuscript data in unconstrained or constrained mode when there is usually space among characters. The engine has been expressly trained on the European and American writing style with an high accuracy.
The BCR Technology allows the recognition of bar codes, decoding their content. It recognizes all the standard bar codes, enclosed the pharmaceutical ones.
It's the recognition technology for printed and typed texts. It's omnifont and it can recognize characters having any font style and size.
This engine works on pre-printed OCR-A codelines of postal and banking documents.
This engine works on pre-printed OCR-B codelines of postal and banking documents.
MICR CMC7 - E13B Technology
This engines works on pre-printed CMC7 or E13B check codelines.
It allows user to read manuscript data in cursive written (natural writing not in capital letters): what was only imaginary a few years ago, now it's real. This feature is essential for reading forms that haven't been expressly designed for the automatic acquisition and contain unconstrained fields, freely written, without any tie.
The AMR allows you to perform the assisted manual data-entry for data you can't or you don't want to read automatically.
Through the IDE system it's possible to export page zones or whole pages in image format. It's very useful when you need to keep portions of forms containing signatures, sketches, drafts or other information, without modifying anything of their characteristics or structure.
Recogniform Reader is available in two versions, according to the way the above production steps are executed:
3. Verify / correction
A "zero" step, prior to the production itself, it's represented by the template definition. What is a template? A template is a "project" that contains all rules and information needed to read properly a specific kind of forms. (For example: the template contains the following information: read a barcode Code39 in the upper left of the form).
It's very simple to create and develop a template, using the very easy-to-use tool called Recogniform Application Designer (included in the software): just design with your mouse the fields area on the empty form, select the kind of data you need to extract (barcode, ocr, icr, omr, etc.) and that's all. Of course you can set a lot of functions and rules using a powerful scripting language that will let you feel really the "owner" of the software:discovering its flexibility and power you will soon imagine a thousand of interesting opportunities.
2. Recogniform Input Station
Recogniform Input Station is the application of Workgroup solution that allows to carry out the data capture of documents acquired by various ways: scanner, fax, file, internet.
Recogniform Input Station allows you to import images in different ways:
You can use monchrome, greyscale or color images. In this last event the system can filter the colors that may interfere with the recognition.
2.2 Input from files
Recogniform Desktop Reader allows to process previously scanned images anda saved in any TIFF format, compressed or not (CCITT G4, CCITT G3, Huffman, PAckbits, JPeg), single or multip-page, as well as in JPEG, BMP, PNG format.
2.3 Input by automatic directory monitoring (with sub-directories also)
You import files by directory monitoring, giving the start to the process automaically at pre-defined interval of time or when a certain nnumber of file is available in the folder.
2.4 Input from internet
You can download from any internet server via FTP with User and password. This means that you can acquire forms from a scanner sited in a different location.
2.5 Input from fax
Fax input is directly supported, without external applications.
3. Recogniform Recognition Station
Recogniform Recognition Station automatically ricognizes the batches ready for recognition. The power of Recognifom Desktop Reader is the possibility to work with the state-of-art Recogniform recognition engines, that can be used togheter also on the same field. As described above, you can use the following engines:
An adequate preventive images elaboration increases the quality of the recognition process and reduces the files sizes, so we introduced a lot of functions covering every specific requirement.
Correction of the slope that sometimes is caused by the scanner when it feed with ADF.
Black Border Removal
Removal of the possible black edges due to the excessive sizes of the scanning area.
Form Alignment and Removal
Alignment of the form to compensate the horizontal and vertical shift; Removal of the pre-printed elements when the form is not printed with blind-ink.
Removal of horizontal and vertical lines rebuilding the characters crossed by them.
Removal of black isolated points and spots.
Field Box Removal
Removal of the box delimiting a single field, if it is not printed with blind-ink.
Character Box Removal
Removal of the box delimiting the single characters of constrained fields, if it is not printed with blind-ink.
Inversion of colours in case of white characters on dark background.
These cleaning functions can be used on the whole image or locally, defining the specific areas to be processed.
4. Recogniform Correction Station
Using a new validation and correction system, the major part of alphabetic fields can be verified and it's possible to solve automatically all doubts generated by ambiguous recognitions.
This system uses statistical information relative to all the possible combinations of three consecutive characters in the target language, analyzing some thousand of words: these combinations are called Trigrams are enclosed and ready to be used: in this way all the trigrams combinations, the allowed one and the forbidden one, as well as their using frequency, are fully and clearly known. For example, if a recognition engine reads the word "SMITK", the system will correct this word changing it into "SMITH", without operator's intervention and with no risk to give a wrong result. In fact, using a new technology called CREP® (Common Recognition Errors Proofing) and with the help of an Artificial Intelligence system, Recogniform Desktop Reader is able to investigate all proofing combinations, selecting the most probable one. All this process takes place in full autonomy.
4.2 E.B.V.® (Eye Blow Verification)
During the definition phase of the application, it's possible to get the manuscript characters or those coming from codelines (all of them or only the suspect ones, whose confidence level is under a specific parametric threshold) to be presented to an operator for a visual verification.Thanks to the Recogniform Technologies exclusive system called Eye Blow Verification®, the operator is able to verify thousands of characters a minute with minimum effort and maximum accuracy. This system is based on the principle that, inside a group of similar elements, the eye is automatically attracted from the different ones. For example, if in a group of people, everybody suits a blue t-shirt except a person who has got a red t-shirt, the last one would be fast noticed without a detailed examination of the whole group! According to these considerations, Recogniform Desktop Reader shows in the same context all the characters recognized and classified in the same manner, so the operator can immediately look and notice the presence of intruders generated by wrong classification. In this way it's possible to find and correct all the possible errors of recognition introduced by: not eliminable dirtiness, defects of scanning, ambiguity, etc. Also in case of ambiguous cases, Recogniform Desktop Reader instantly allows you to solve the problem, automatically recalling on the video the image of the whole field.
4.3 Visual Assisted Verify
After the characters verification, the phase of fields correction starts, visualizing in the same context both data and the relative image, so they can be compared directly.
To save time in comparison operations, we have added an option that allows user to listen read data from the computer, using the text-to-speech technology: in this way, instead of reading data two times, the operator can read just the data on the image, listening from the computer the read data.
4.3.2 Correction and Accuracy
It's possible to decide which fields need correction: all; only those whose level of esteemed accuracy is under a certain threshold; nobody. It's also possible to set for each field a different confidence level.
Before being stored, the read data can be formatted in several ways, allowing the output to adapt to any necessity: conversion to uppercase or lowercase, empty spaces deletion, characters substitution, addition of suffix or prefix, etc.
4.3.4 Lookup tables and dictionaries
In addition to database formats and .txt files, you can also use compressed dictionary .dct for the look-up functions. These files are characterized by high speed of access, small memory consuming and don't need settings of alias, etc.
To create a .dct file, there is a specific utility that receives in input an ASCII file (a word for each row). Look-up speed is very high: hundreds of thousands of comparisons a seconds. Compression is around millions of words / Mb.
The following .dct dictionary are available fot the following countries (including first names, last names, zip codes, streets, towns, etc.) :
other countries avaible on request
Moreover you can easily create your personal dictionary.
When you scan images with blind ink (red/green/blue) you may need to re-build the original image in order to get a perfect idea of the original form. This may be useful, for example, to correct check boxes fields. With Recogniform Reader you will be able to get an image with overlay, overlaying the black ink of the form scanned on a color/greyscale/black and white empty form.
5. Recogniform Output Station
Recogniform Output Station allows a flexible use of the recognized data thanks to the possibility of exporting them to the applications in different ways. It's possible to export data in three different ways: to databse, to file or to applications.
Output to database::
Microsoft SQL Server
Output to file:
ASCII text (.txt) (.asc)
Comma Separed Value (.csv)
Tab Separed Value (.tsv/.tab),
Hypertest Markup Language (.htm/.html)
Extensible Markup Language (.xml)
Microsoft Excel (.xls)
Symbolic Link Interchange Format (.slk/.sylk)
Portable Document Format (.pdf)
6. Recogniform Control Server
Recogniform Workgroup Reader allows user to work in a client/server configuration: as Recogniform Desktop reader, it uses a job-oriented approach, grouping documents in batches. The Control Server tracks every batch's process progress, centralizing the storage and managing the workflow. A batch can contain any number of documents. Each batch's process is structured as follows:
Fields correction (comparison between data and image)
Post-processing (data transformation and normalization)
Data output (storing in files or in databases)
7. Customization by scripts
Recogniform Desktop Reader allows user to set in a visual way all the necessary parameters for the data capture of data. It also has a sophisticated events oriented scripting language, useful for matching particular needs. With this language you can associate a specific procedure written by user to each scheduled event, modifying the standard behaviour of the program or integrating new features. It's very similar to Basic and to Pascal so it's very easy to learn and user-friendly. This language includes in its syntax conditional expression (IF.), cycles (FOR., REPEAT. and WHILE.) and uses thousands of integrated functions. The system can automatically set specific variables, allowing effective interaction between the application and the process of optical recognition. This feature gives you the possibility to implement new personal features like controls of squaring between fields, multiple readings of the same field with different pre-processing options, or output of personalized layouts. With this system you can get a strongly customized application starting from a standardized product. The advantages are as simple as great: small costs and better reliability and flexibility.
Recogniform Desktop Reader allows user to record automatically all statistical data relative to each job in a log file, that can be centralized in case of multiple installations.
The information stored are:
Starting date and time
Automatic reading time
Characters verification time
Fields correction time
Processed forms number
Number of correctly read fields
Number of suspects fields
Number of corrected fields
Number of correctly read characters
Number of suspects characters
Number of corrected character
Using the module Recogniform Statistics Viewer it's possible to analyze data automatically, getting printer-friendly detailed graphics containing meaningful information about the productivity and the efficiency of your processes.
The graphics can refer to all the jobs or only to a specific job. They show:
Number of processed forms for workstation
Number of processed forms for user
Number of processed forms per day
Number of processed forms per type
Working time for workstation
Working time for user
Working time for day
Working time for type
Distribution times of reading, verification and correction
Total read characters, suspects and corrected ones
Total fields read, suspects and corrected ones
It's also possible to use filters to analyze only the data ref. to a specific workstation and/or user and/or type and/or day.Moreover, the statistical data can be exported in .csv files to be analyzed with other applications.
Briefly, with this system it's possible to monitor users' productivity by a complete set of statistics in a way detailed and global at the same time.