Source Image Recommendations

The best recognition results can only be achieved if the source image is of good quality. To ensure that users of your application receive the best possible results, you need to pay some attention to the quality of input images.

You can implement some basic quality-checking features, display tips for best image quality in the user interface, and include advanced recommendations in the user's manual. If your application contains a scanning interface, you can also control the scanner settings.

Check input image quality

When your application receives an image for recognition, one of the first steps can be checking the image resolution. If the resolution is too small (lower than 150 dpi), some image details might be lost, and the recognition quality will deteriorate. If, on the other hand, the resolution is too great (greater than 600-700 dpi), loading and processing the image will take more time, while the recognition quality will not be materially improved.

In both these cases, your application should display a warning to the user:

  • The image resolution is too small, please re-scan with a resolution greater than 150 dpi
  • The image resolution is too great, please reduce the image resolution

Next, you can implement some algorithms for estimating the image brightness. When the image, on average, is very light, some parts of the text may be irretrievably overlighted; when the image is very dark, some parts of the text may be obscured by dark patches. Either of these defects can affect the recognition quality. Display a message to warn the user that the results may not be good enough and/or prompt them to provide another digital version of the same document.

If your application implements image preprocessing before recognition (see the methods of the ImageDocument object), display a message to discourage the user from editing the images they receive from a scanner or digital camera. Any edits that are performed on the image may lead to losing the details necessary for recognition.

If an image your application processes was received from a digital camera, it will most probably contain some EXIF information; you can check this to find out if the flash was used when the picture was taken, and again display a warning to the user about bad effects the flash could have on recognition results.

Control the scanner settings

If your application can receive images directly from a scanner and manage the scanning operations, you need to select the best defaults for scanning and advise the user as to how to get good quality scans. The following settings are recommended

for the ScanSourceSettings object:

  • set the BrightnessControl property to SBC_Fine to let ABBYY FineReader Engine select the best brightness value; alternatively, use the SBC_Manual constant and set the Brightness property to a reasonable medium value, for example, 50;
  • set the Resolution property to 300 dpi;
  • if the color of the documents is not important for the task, set the ColorMode property to SCM_Grayscale: scanning in black-and-white will not always produce the best results, especially if the original document is not of very good quality.

Recommendations for inclusion into the user's manual

The user's guide for your application can include the recommendations on how to obtain good quality digital versions of their documents.

You can find our tips in the following sections:

See also


Improving Recognition Quality

24.03.2023 8:51:52

Usage of Cookies. In order to optimize the website functionality and improve your online experience ABBYY uses cookies. You agree to the usage of cookies when you continue using this site. Further details can be found in our Privacy Notice.