Form Recognition Settings
As of version 1.1 which was released in June 2010, FormReturn's recognition settings will detect either a single checkbox or multiple checkboxes with complete checkbox selection. The new detection algorithm is very robust, which means heavy lines and borders added near the mark areas won't affect the detection of response data during the data capture process.
Recognition Settings for FormReturn version 1.0.7 and previous versions.
What Recognition Settings are Used for.
FormReturn OMR has default Recognition Settings which are used by the form processor for determining which checkbox /es contain response marks. They are:
These default settings work on percentages and are normally the correct settings that will detect marks made in checkboxes. They won't have to be changed unless the marked checkbox failed to be detected, (or was detected when it shouldn't be), in a test preview of the form template.
Because all scanners are different, the quality and crispness of your scanned images, as well as the darkness of the pen or pencil used by the respondents are factors that could affect the recognition settings.
How Marks in Checkboxes are Detected.
The Mark Threshold Setting determines which checkbox /es will be
counted as marked. The form processor counts the number of white pixels
and the number of black pixels in a checkbox and it's surrounding
fragment padding. When the Mark Threshold is set at 40%, which is the
default setting, any checkbox which has a pixel count of 40% more
black pixels than white pixels, will be counted as a marked checkbox.
Reasons Why Hand-marks made in Checkboxes May not be Detected.
If marks in checkboxes aren't properly detected, the problem could be the
quality of the scanned form images produced by your scanner. A quality, clear scanned image is required so that the darkness of the marked checkboxes can be detected by FormReturn.
If a pencil or light colored pen
was used by the respondents to make the marks in checkbox, the luminance created when the image is
scanned causes errors in the detection of the mark by the form processor. The luminance causes more white pixels to be counted which reduces the mark threshold between the number of white pixels compared to the number of black pixels counted.
A Test preview
using an image from your scanner before Publishing a form template will determine if the detection of hand-marks will be accurate. The Luminance and Mark Threshold Settings can be increased until the marks are determined accurately by FormReturn.
Any changes you make to the Recognition Settings will be
saved to the form template publication and used in processing of the
returned forms from that publication.
The Recognition Settings Panel
The Recognition panel where recognition settings can be changed.
Recognition Setting Screencast.
Test your Recognition Settings
Click on the print button in
Print Preview and print a form from the template to test the Recognition settings from scanned form images from your scanner, before the publication of the form template. Hand mark some of the checkboxes on the form using the same color pencil or pen that your respondents will be using, scan it and save to your computer, then open it by browsing for it in Test preview.
The test preview image determines the quality of images from your scanner and tests if
the default recognition settings will accurately detect hand marks in
checkboxes. If a pencil was used to mark the checkboxes, the Luminance setting may need to be changed if the hand-marks aren't detected properly.
The Mark Threshold can be changed if the % of black pixels counted in any checkbox isn't 40% or more greater than the counted white pixels in any checkbox.
Note: Any adjustments you make to the Recognition Settings, will be saved to the form template and used for processing of the returned forms.
Preview the Scanned Test Image:
- Open your form template in the Form Editor and click the Recognition Preview Tab.
- Click the Test Preview Tab
- From the Test Preview application window, browse for the scanned form image on your computer and open it.
Check Detect Marks in the Preview Check panel.
The checkboxes which were handmarked should be shown as marked by FormReturn. If the checkbox with the mark value of D was marked then the recognition test should read as Marked:(D)
What to do When Handmarks in Checkboxes aren't Detected
If there is an error in detection of a marked checkbox, click on the mark area to open the Mark Detection Details dialog.
If any of the marks weren't accurately detected, then the Mark Threshold and Luminance settings can be changed or try re-scanning the form using a higher resolution setting or contrast setting on your scanner.
The Mark Threshold is increased if the number of black pixels counted isn't 40% higher than the number of white pixels counted from the shading in any checkbox.
The Luminance setting is increased if a pencil or light colored pen was used to make the marks in the checkboxes. Making the luminance setting too high can cause little black dots to appear on the scanned image that shouldn't be detected.
Re-scanning your form, Increasing the resolution and / or contrast settings on your scanner can make a more clearly defined scanned image which will increased detection of the barcodes and hand-marks made in checkboxes.
Mark Detection Details
Click on any mark area to open it's Mark Detection Details dialog.
FormReturn counts the number of pixels in each checkbox, that means the
white pixels, the black pixels and any black pixels that continue
outside the checkbox within the fragment padding).
Mark Area - Zoom in on the checkboxes to see how the black pixels were counted.
Silhouettes panel - See the pixel count and the Threshold percentage difference between white and black pixels for each checkbox.
Mark & Score Calculation.
Mark Area Panel
Zooming in on the mark area will show you the quality of your scanned image and how much of the shading was determined as black by FormReturn.
Silhouettes Panel
- Pixels - The number of black pixels counted for each checkbox in the area.
- Enclosed - The total number of pixels counted (black and white) for each checkbox in the area.
- White - The number of white pixels counted for each checkbox in the area.
- Threshold - The percentage of black pixels more than white pixels counted for each checkbox in the area. Because the threshold is set at 40%, all checkboxes with 40% more black than white pixels will show as detected.
- Value - The mark value for each checkbox in the area.
The Mark and Score Calculation Panel
- Mark Threshold - setting that was used for the publication.
- Detected Marks - Mark value of the detected checkbox.
- Aggregate rule - set for the detected checkbox.
- Calculated Score - Score given to the detected checkbox using the Aggregate Rule.
- Field Name - Captured Data Fieldname given to the detected checkbox.
Why Wasn't the Marked Checkbox Detected.
If the mark threshold is set at 40% but the shaded checkbox black pixel count comes to less than 40% more than the white pixel count, then the shaded checkbox won't be detected as marked.
Example: If the medium used to handmark the form was pencil or the quality of the scanned image is poor, the Luminance and Mark Threshold settings can be changed so the marked box can be detected.
Luminance
The luminance setting is the cut off point at which the pixels in checkboxes are
determined as black or which pixels are determined as white. Some
shades of grey can be determined as either black or white.
The Luminance setting is used to darken the scanned form image when it has been scanned in color. If the form was marked with a pencil, some of the lighter grey shading may be counted as white pixels instead of black. Increasing the the luminance setting to around 190 will cause more black than white pixels to be detected.
If the luminance setting isn't set high enough for FormReturn to detect handmarked shading in the mark area as black, increasing it will detect more of the lighter shadings such as pencil as being black. Selecting the "1 Bit View will show how much of the mark is detected as black.
Checking the 1 Bit View box will show the image in black and white, which is how the form processor will determine the black from white.
Note: If the Luminance is set too high, it will cause black pixels to appear on the image where they shouldn't, leading to detection errors. Ideally the Luminance setting can be set anywhere between 90 and 190, but this will depend on the quality of the images your scanner produces.
Mark Threshold
The percentage that the Mark Threshold is set at is used by the form processor to detect the marked checkbox or checkboxes. The default threshold is 40% which means any checkbox with a count of 40% more black pixels than the white pixels, will be detected as a marked checkbox.
This will allow for single checkboxes added to the mark area to be detected if they have been marked by the respondent.
Click on the checkboxes to open the Mark Detection Details dialog.
Use the zoom tool in the mark area panel to see how the pixels were detected and counted. This will help you to understand why a mark wasn't detected when it should have been, or if a mark was detected when it shouldn't have been.
If the threshold wasn't set high enough, increase the setting to see the difference in the pixel count in the silhouettes panel.
Fragment Padding
Select Detect Fragments from the Preview Check panel.
The Fragment padding is the white area between the checkbox borders and the red detected Fragment border.
Increasing the Fragment Padding setting, increases the white area around the checkboxes.
The advantage of increasing the Fragment Padding, is if the scanned image quality isn't very good it improves detection because more of the Fragment area is captured in the data capture process.
The disadvantage of increasing the Fragment Padding is that it takes up more room on the form. If any other areas on the form touch or overlap the edges of the Fragment area, the risk is taken that the detection of the boxes could be broken.
Deskew Threshold:
It is highly recommended that the automatic Image Deskew box is left checked, unless you are completely sure your images were scanned in straight.
Keeping the Perform Deskew box checked, will automatically perform a Deskew. The setting determines the angle at which FormReturn will perform the deskew of a scanned image.
The Deskew Threshold setting indicates the angle at which an automatic deskew will be performed.
When the Deskew Threshold is set at the default of 1.05, FormReturn will automatically perform a Deskew if the Image is
more than 5 deg. skewed.
The Skew of the scanned Image is detected and is shown in degrees.
-0.03 deg skew means the form was scanned in on a slight angle which isn't enough for an auto deskew to be performed as it isn't enough to cause problems.