Forms often contain preprinted elements as field rakes (or combs) or character rakes (or combs). Scanned document in some cases, also have horizontal or vertical lines due to the banding or folding of papers. Dealing with those artifacts is a challenging task for a system that tries to detect rakes during processing business documents.


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 or rakes)
page orientation detection and correction
layout analysis
classification
character recognition

Each step must be completed well enough for the performance of the sequence and result to be successful. Steps that follow the rake removal are inefficient if the correction fails.

RakeHelper searches for rakes the aim being the extraction and recognition of the characters. Also rakes can be used as features in the step of form identification and recognition as anchor elements.
RakeHelper expects as input a monochrome image.