Module name:	MAT
Module identifier:	RM_MAT
Filling methods supported:	FM_OCRA, FM_OCRB, FM_MICR, FM_DOTDIGIT, FM_DASHDIGIT
Filters supported:	all elements except FILTER_LOWERCASE
Trade-off supported:	none
Knowledge base file:	`SFOCR.TUD`
Training file supported:	no

This module is supported on: Windows.

This module is supplied in both the Professional Recognition Kit and the OCR Kit. Its inclusion in your application must be covered by distribution licensing. See the topic on Licensing in the General Information help system.

Application areas

This module is designed to read certain groups of fixed-font characters specially designed for OCR or imaging applications, in which no two characters have similar shapes. Each character group has its own filling method. Application areas are in banking, check or waybill handling, product distribution and document validation, where high accuracy can be vital. It also handles some non-fixed print styles.

Range of characters

The above-mentioned supported filling methods cover the ranges of characters the MAT engine knows. The description of these ranges can be found in OCR special filling methods and in the summary table of OCR Special Characters.

Accuracy issues

When this module is handling fixed fonts, well printed on a firm surface, with a limited number of possible characters, it should provide high accuracy recognition. This module doesn’t interpret the page-level recognition trade-off settings. This recognition is fairly tolerant of differing resolution settings. The dot- and dash-digit symbols are typically printed onto product containers, which may be curved or molded; furthermore many different standards are used. For high accuracy here, the texts to be read should be found on flat surfaces (on packing documents rather than product containers).

If the application does not need spell checking it can be switched off using kRecSetSpell, this may increase the module's performance.

Conditions

This module supports the checking module fully, and also all filter elements (however, FILTER_LOWERCASE will have no effect). Characters should be at least 4 x 8 pixels large and should not be touching. FM_OCRA and FM_OCRB support both single and multi-line zones, the other filling methods (FM_MICR, FM_DOTDIGIT and FM_DASHDIGIT) do not: each line must be zoned separately. MICR strings found on checks are usually single-line only.

Zones with FM_OCRA or FM_OCRB filling method can have either single or multi-line content. By default, for these types of zones, the MAT recognition modules assume multi-line content, but it can be controlled from an INI file like this

        [Parameters]
        ; SingleRow specifies whether the zone contains one text-line only.
        ;   Parameter range: [0, 1]
        ;   This parameter has an effect with FM_OCRA or FM_OCRB fillingmethods.
        SingleRow = 0

The path of this INI file can be specified in a setting Kernel.Ocr.MAT.SpecParam.