Foreground-background regions guided binarization of camera-captured document images

Syed Saqib Bukhari, Faisal Shafait, Thomas Breuel

In: 3rd International Workshop on Camera Based Document Analysis and Recognition. International Workshop on Camera-Based Document Analysis and Recognition (CBDAR-2009) July 26-29 Barcelona Spain Seiten 18-24 On-Line 2009.


Binarization is an important preprocessing step in sev-eral document image processing tasks. Nowadays hand-held camera devices are in widespread use, that allow fast and flexible document image capturing. But, they may pro-duce degraded grayscale image, especially due to bad shading or non-uniform illumination. State-of-the-art binarization techniques, which are designed for scanned images, do not perform well on camera-captured documents. Further-more, local adaptive binarization methods, like Niblack [1], Sauvola [2], etc, are sensitive to free parameter values, which are fixed for whole image. In this paper, we de-scribe a novel binarization technique using ridges-guided local binarization method, in which appropriate free pa-rameter value(s) is(are) selected for each pixel depending on the presence or absence of ridge(s) in the local neigh-borhood of a pixel. Our method gives a novel way of auto-matically selecting parameter values for local binarization method, this improves binarization results for both scanned and camera-captured document images relative to previous methods. Experimental results on a subset of CBDAR 2007 document image dewarping contest dataset show a decrease in OCR error rate using reported method with respect to other stat-of-the-art bianrization methods.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence