Auto-OMR
Auto-OMR is used to process large and complex Optical Mark Recognition (OMR) regions on standardized forms. Rather than specify each region to search for marks, as with standard OMR, you can specify a sample feature such as a bubble or checkbox and Auto-OMR will automatically detect similar markable features in a specified area of the image. Auto-OMR can also handle multiple choice checkboxes. In addition to determining whether or not a particular feature is marked, it can determine which of a group of features is marked and assign a value accordingly. Auto-OMR can be used in Pre-Classification Processing, First Page Identification, Page Processing, Last Page Identification, or Post-Processing.
Example: Golden State Financial Advisors uses slipsheets with checkboxes indicating whether the documents are letters, prospectuses, statements, or reports. Rather than configuring a zone around each checkbox, they use Auto-OMR to detect and create zones around all the checkboxes. Depending on which checkbox is marked, the value of the token from the Auto-OMR process is "letter," "process," statement," or "report."
To configure Auto-OMR
- In the Session Configuration Pane, select the stage of processing where you want to use Auto-OMR.
- In the Tasks Pane, select Auto-OMR.
- You can optionally enter a name for the process under Process Name.
- Move through each step of the wizard at the bottom of the pane. You can also click Skip Wizard to display and configure the properties all at once.
- Master Form Selection: The master form is an image of a blank form that matches the forms you will be processing. You will use the master form to define which region should be searched for marks. There are three ways to add a master form:
- Scan: Scan in the Master Form using the currently configured scan source.
- Import: Import an image that is currently stored in a network drive.
- Copy from a sample image: If you have already added a custom sample image that is the same image you want to use as the master form, you can copy it.
- Page Range: When configuring this process in Page Processing or Post-Processing, you will be prompted to specify a page range. In other stages, default settings will be automatically applied.
- OMR Collections: In this step, specify an area of the image to search for markable features. You can have more than one collection per page.
- To define an area, click Add. This will open the OMR collection sub-wizard.
- Collection Name: Specify a name for the collection. The name will also be used in the tokens generated by the process.
- Grouping: Choose whether to group the features. If grouped, they will function as a multiple choice selection and you can specify what values will be returned if the regions are features. If not, each feature will be independent and will return a value depending on whether it is marked or unmarked.
Note: Auto-OMR does not support vertical groups.
- Token Name Format: In this section, you can customize the tokens that will result from this process. By default, the name is Group %(Index), so upon processing the names will appear as Group 1, Group 2, Group 3, and so on. You can change the naming convention by typing in the Name box. You can also adjust the starting count.
- Search: Configure the zones around a sample markable feature, such as a bubble or checkbox, and the area that will be searched for marks that match the sample.
- Token Values: The available token values depend on whether you chose to group the features. If the features are grouped, you can specify a value to be returned for each feature if it is marked, and a default value that will be returned for any unmarked feature. If the features are not grouped, each feature will return a value depending on whether it is marked or not. The default values are true for marked and false for not marked, but you can specify different values.
- To add another OMR collection, click Add. To modify an existing collection, select it and click Edit.
- Anchor Adjustment: Due to variations in printing and scanning, the Auto-OMR zones may not be aligned with the rest of the form. The Anchor Adjustment setting determines how much the region to be recognized to match the master form. Select None, Low, Medium, or High, or specify a level from 0 to 10.
- Confidence Level: Select the percent by which an image must appear marked to be considered a successful mark. A low confidence level can help compensate for faint marks, and a high confidence level can help compensate for low-quality images.
- Low (65%): Faintly marked regions will be reported as marked.
- Medium (80%): Most marked regions will be reported as marked.
- High (95%): Only clearly marked regions will be reported as marked.
- Custom: Specify a value from 0 to 100. A confidence level of 1 will report even unmarked regions as marked.
- Alignment Method: Choose which components of an image will be used to match it to the master form.
- Lines: Use lines to match the image to the master form.
- Text: Use text to match the image to the master form (horizontal text only).
- Lines & Text: Use both lines and text to match the image to the master form.
- Identification Condition: When configuring Auto-OMR in First Page Identification or Last Page Identification, you will be prompted to specify an identification condition for how the process will be used to assign documents to the document class.Sample Documents
- Optional: To preview how this enhancement will affect scanned images and OCRed or extracted text, test processes. For the best results, add a custom sample page before testing. Adjust and test until you are satisfied with the results.
Note: Local image enhancements can be used with Auto-OMR.
Note: When using percentages to define zone sizes, changing the size of the scanned page (e.g., 8.5 x 11 to 8.5 x 14) will also change the placement and size of the zone.
