User Guide

1. Dropout form
All the fields on the form are white rectangles on a color background. The important thing here is the color
used, as it disappears during the scanning process (see recommendations on color choice in Appendix
III), leaving only the field contents and reference points on the form image for the recognition module to
recognize.
Dropout forms are the preferred choice in terms of recognition quality.
2. Raster Forms
Field borders on raster forms are termed raster lines – i.e. lines made up of a series of dots located at equal
distance from each other. The size and the location of these dots are determined manually (see
"Black&white forms with raster backgrounds" (page 9) and "Black&white forms with raster borders" (page
9)) . These dots are retained on the image after scanning, but the system treats them as garbage and
removes them automatically during image cleaning, leaving only field contents for the recognition
module to recognize.
3. Black&white Linear Forms
Field borders in this case take on a normal appearance (i.e. are black solid lines) and remain on the image
after scanning. That means that the block image includes both field borders and field contents, and the field
contents separation task is carried out by the recognition module. Hence recognition quality will depend to
a large extent on how neatly the form was completed (see "Black&white linear forms" (Page 10).
That’s why we do not recommend the use of black&white linear forms for automated processing.
Let’s turn to the advantages and disadvantages of the following types of forms:
• dropout color forms (as well as gray forms);
• raster forms: containing raster lines as field borders and forms with raster backgrounds;
• black&white linear forms.
Dropout color forms
Dropout color forms - these are forms in which fields are represented by a series of white rectangles (or other white
geometrical shapes) on a color background. The background is usually “red-orange” or “green” in color, and
disappears if the scanner has a special driver which can filter colors (in the case of color scanners), or a color-
filtering lamp (in the case of a non-color scanners).
(a) (b)
Ideally, all form elements, with the exception of reference points, disappear during scanning, leaving only field
contents for recognition on the form image.
How is this done? By ensuring that not only the background but also the explanatory information is printed in the
dropout color (see figure (а)).
Scanning
The scanning of forms with “red” and “green” background is performed either:
a. on a color scanner with color filtering software (red or green)
b. on a non-color scanner using a red or green lamp (hardware color filtering takes place in this case).
c. on a non-color scanner using a white lamp and with a red or green filter (filtering quality in this case is
much lower, as the background may not disappear completely, or field contents may be inadvertently
removed).
Notes.
1. Many color scanners also have blue software filtering. We do not recommend the use of blue forms,
however, as forms are likely to be completed using both black and blue ink. Field contents written in blue
ink will disappear in this case.
2. Should you use a standard white lamp with no color filtering to scan your forms, various light colors (not
only “red” or “green”, but light yellow and other similar colors) are also likely to dropout. That means you