The page orientation of a document is defined as the printing direction of text lines. Therefore the page orientation can be in either horizontal printing mode (portrait mode) or vertical printing mode (landscape mode). The page orientation correction is crucial for any automated entry system for printed documents. LandscapeHelper detects landscape pages (rotated with 90 degrees) and automatically put the image into the right position for further processing steps (character recognition).
The document structure analysis and character recognition are usually done in several phases:
scanning
thresholding
skew detection and correction
despeckle or speckle removal
line removal
border removal
detection of preprinted elements (like boxes)
page orientation detection and correction
layout analysis
classification
character recognition (normal and inverse)
Each step must be completed well enough for the performance of the sequence and result to be successful.
LandscapeHelper expects as input a monochrome image.
