Advanced OCR Recognition Settings
Use this window to specify advanced OCR recognition settings that apply to recognition operation.
Performance vs. Accuracy
Select a recognition output format for your documents.
The following is the list of recognition engine modes:
-
Maximize performance: This mode provides the maximum recognition engine performance, but with a reduction of accuracy optimization. Selecting this mode provides a faster performance for scanning in similar images than the "Balance accuracy with performance" or "Maximize accuracy" options.
-
Balance accuracy with performance: This mode balances the recognition engine's performance and accuracy. Selecting this mode provides better recognition accuracy than the "Maximize performance" option. (Default)
-
Maximize accuracy: This mode provides the highest accuracy optimization, but the performance of the recognition engine is at a minimum. Selecting this option provides better recognition accuracy and quality than the "Maximize performance" or "Balance accuracy with performance" options.
Image Settings
Rotation
If you process documents that face in a non-standard direction (such as sideways or upside-down) as they pass through the Kofax OmniPage OCR, you can use the Rotation setting to digitally adjust the rotation of these documents.
For example, if all documents are loaded in the same orientation, you can adjust that orientation by selecting 90 degrees, 180 degrees, or 270 degrees.
If the orientation of these documents varies, you can select Auto (Default) to adjust the rotation based on the detected orientation of bar codes and/or text content in each document. For example, Kofax VRS may detect English text that has been scanned sideways. Based on that assessment, the image is automatically rotated 90 degrees.
The Auto option eliminates the need to presort batches before scanning to ensure that the documents are facing in the same direction. The images are automatically rotated as you scan.
The Auto option can detect text content in English, French, Italian, Spanish, and German, as well as Arabic, Cyrillic, Greek, and the Asian languages. The Auto option is not effective for images without text content and may adversely impact performance.
Resolution Enhancement
Select one of the following options to enhance the original image resolution and improve the recognition quality.
| Resolution enhancement option | Description |
|---|---|
|
No (default) |
No resolution enhancement is applied. |
|
Yes |
Enhancement is applied with the ratio of 2:0. |
|
Legacy |
The ratio of enhancement depends on the resolution of the non-BW (black-and-white) image. If the resolution is 160 DPI or less, the ratio of 2:0 is applied. If the resolution is between 160 and 210 DPI, the ratio of 1:5 is applied. |
|
Standard |
The ratio of enhancement is detected dynamically: it depends on the resolution and the detected average character size of the non-BW image. If the resolution exceeds 210 DPI, the enhancement is not applied. |
|
Auto |
The ratio of enhancement depends on the current operation setting that can be configured to optimize accuracy or performance. |
Text Type
You can define the text type to be recognized.
If the text on the recognized image uses a font based on the CMC7 or E13B text type, we recommend that you select the respective option as listed in the following table. For best results, and to avoid incorrect recognition, do not select the Automatic option for use with CMC7 or E13B.
| Text type option | Description |
|---|---|
|
Automatic |
Automatically detects the type of text. |
|
Handprint |
Presumes that the text on the recognized image is handwritten. |
|
CMC7 |
Presumes that the text on the recognized image is a magnetic ink character recognition font based on the CMC-7 (ISO 1004) industry standard. |
|
E13B |
Presumes that the text on the recognized image is a magnetic ink character recognition font based on the E13B industry standard. |
|
Machine print (default) |
Denotes a machine-printed text with any typeface not highly stylized. |
|
Matrix |
Presumes that the text on the recognized image is printed on a dot matrix printer. |
|
OCR-A |
Presumes that the text on the recognized image uses the OCR-A font. The font is most commonly used in passports and bank checks. |
|
OCR-B |
Presumes that the text on the recognized image uses the OCR-B font. The font is most commonly used in passports and bank checks. |