Document imaging must address two types of skew; paper skew and print skew. Paper skew relates to the relationship between the paper and the scanner camera as the paper is scanned. If the paper is skewed, the image is skewed. Paper skew typically is introduced by scanner auto-feeders and to a lesser extent, their internal paper transports. Some scanners control paper skew well; others do not.

Print skew relates to how the print actually was deposited on the paper. In other words, print skew relates to the relationship between the print and the paper it's printed on, not the paper and the scanner camera. Photocopied and faxed documents tend to have skewed print.

Deskewed images enhance OCR capabilities and significantly increase document readability

The solution is to electronically deskew the image by reorienting image pixels along a corrected x/y axis. This technology usually is very effective; though in a small number of cases, it can introduce unacceptable distortion.

Some scanners can automatically match the size of the captured image to the size of the paper and do not require border cropping. Many scanners cannot match the size of the captured image to the size of the paper scanned, thus they produce an ugly black area around the actual image. Image cropping removes extraneous black borders, either by requiring a human operator to manually define the area to be cropped, or by employing sophisticated algorithms to evaluate the image and automatically crop borders algorithms to evaluate the image and automatically crop borders.

Scanners often will interpret minor paper imperfections such as extraneous dots as small groups of black pixels called background noise. Carbon forms are excellent examples of paper with significant amounts of background noise.

Background noises renders bitonal images less readable and image file compression schemes much less efficient.
Noise removal algorithms examine an image, identify black pixels likely to constitute background noise and convert them to white pixels. The result is a more readable image and a smaller compressed file size.

Most documents require background removal of vertical lines, horizontal lines and background shading that contribute no substantive data. Removal of background noise can make the image more readable and dramatically reduce file size.

Background removal algorithms are available but consideration must be taken in using them. It is not easy to predict when a vertical or horizontal line might in fact be critical in conveying the data represented in an image. We recommend employing the technology only where all images to be processed have been tested and the results evaluated.