Adaptative Smart-Binarization Method for Images of Business Documents
Résumé
The automatic reading systems of business
documents requires fast and accurate reading of interest zones using
the OCR technology. The result quality of the binarization has a
major impact on the quality of binary characters. We propose in this
paper a smart-binarization method of the images of business
documents. In our work, we considered different degradations on
document images, real-time constraints and high spatial resolution of
the images. The quality of each pixel is estimated using a hierarchical
local thresholding in order to classify it as foreground, background or
ambiguous pixel. The ambiguous pixels that represent the degraded
zones cannot be binarized with the same local thresholding. The
global quality of the image is thus estimated from the density of
theses degraded pixels. If it is considered as degraded, we apply a
second separation on the ambiguous pixels to separate them into
background or foreground. This second process uses our improved
relaxation method that we have accelerate for the first time to
integrate it into a system of automatic reading document. Our
approach, compared to existing binarization approaches (local or
global), offers a better reading of characters by the OCR. The
computation time remains constant with the variation of the local
window size through the use of integral images. The method was
developed in the context of DOD project (Documents On Demand)
at the request of the ITESOFT company.