Adaptive document image binarization

https://users.iit.demokritos.gr/~bgat/PatRec2006.pdf

Adaptive degraded document image binarization

A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture. The problems caused by noise, illumination and many source type related degradations are addressed. The algorithm uses document characteristics to determine (surface) attributes, often used in document segmentation. Using characteristic analysis, two new algorithms are applied to determine a local threshold for each pixel. An algorithm based on soft decision control is used for thresholding the background and picture regions. An approach utilizing local mean and variance of gray values is applied to textual regions. Tests were performed with images including different types of document components and degradations. The results show that the method adapts and performs well in each case.

Adaptive document binarization

Historical document collections are a valuable resource for human history. This paper proposes a novel digital image binarization scheme for low quality historical documents allowing further content exploitation in an efficient way. The proposed scheme consists of five distinct steps: a pre-processing procedure using a low-pass Wiener filter, a rough estimation of foreground regions using Niblack’s approach, a background surface calculation by interpolating neighboring background intensities, a thresholding by combining the calculated background surface with the original image and finally a post-processing step in order to improve the quality of text regions and preserve stroke connectivity. The proposed methodology works with great success even in cases of historical manuscripts with poor quality, shadows, nonuniform illumination, low contrast, large signal- dependent noise, smear and strain. After testing the proposed method on numerous low quality historical manuscripts, it has turned out that our methodology performs better compared to current state-of-the-art adaptive thresholding techniques.

/pdf/an-adaptive-binarization-technique-for-low-quality-38tb9jvlqy.pdf

An Adaptive Binarization Technique for Low Quality Historical Documents

This paper proposes an algorithm to clean up a large collection of historical handwritten documents kept up in the National Archives of Singapore. Due to the seepage of ink over long period of storage, the front page of each document has been severely marred by the reverse side writing. Earlier attempts have been made to match both sides of the page to identify the offending strokes originating from the back so as to eliminate them with the aid of a wavelet transform. Perfect matching, however, is difficult due to document skews, differing resolutions, inadvertently missing out reverse side and warped pages during image capture. An approach is now proposed to do away with double side mapping by using a directional wavelet transform that is able to distinguish the foreground and reverse side strokes much better than the conventional wavelet transform. Experiments have shown that the method indeed enhances the readability of each document significantly over after the directional wavelet operation without the need for mapping with its reverse side.

Document image enhancement using directional wavelet

A binarization method is presented to counter the stroke connectivity problems of characters arising from mid-level-quality binary image scanning systems. In the output of a binary image scanning system, separate strokes may look connected if the point size is small and the character strokes are complex while strokes may lose connectivity if they are generated at low intensity. Also, erroneous recognition may result if a blemished document surface distorts the image. To counter these problems and to further enhance the quality of character recognition, the authors have developed an integrated binarization scheme, exploiting synergistic use of an adaptive thresholding technique and variable histogram equalization. This algorithm is composed of two components. The first removes background noise via gray level histogram equalization while the second enhances the gray level of characters over and above the surrounding background via an edge image composition technique.

Heok-Gu Kim

Papers

Improved binarization algorithm for document image by histogram and edge detection