Document Image Binarization Based on Texture Features

Binarization has been difficult for document images with poor contrast, strong noise, complex patterns, and/or variable modalities in gray-scale histograms. We developed a texture feature based thresholding algorithm to address this problem. Our algorithm consists of three steps: 1) candidate thresholds are produced through iterative use of Otsu's algorithm (1978); 2) texture features associated with each candidate threshold are extracted from the run-length histogram of the accordingly binarized image; 3) the optimal threshold is selected so that desirable document texture features are preserved. Experiments with 9,000 machine printed address blocks from an unconstrained US mail stream demonstrated that over 99.6 percent of the images were successfully binarized by the new thresholding method, appreciably better than those obtained by typical existing thresholding techniques. Also, a system run with 500 troublesome mail address blocks showed that an 8.1 percent higher character recognition rate was achieved with our algorithm as compared with Otsu's algorithm.

[1]  Andrew K. C. Wong,et al.  A new method for gray-level picture thresholding using the entropy of the histogram , 1985, Comput. Vis. Graph. Image Process..

[2]  Azriel Rosenfeld,et al.  Threshold Evaluation Techniques , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Anil K. Jain,et al.  Goal-Directed Evaluation of Binarization Methods , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[5]  Josef Kittler,et al.  On threshold selection using clustering criteria , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Sargur N. Srihari,et al.  Document image binarization based on texture analysis , 1994, Electronic Imaging.

[7]  Sang Uk Lee,et al.  A comparative performance study of several global thresholding techniques for segmentation , 1990, Comput. Vis. Graph. Image Process..

[8]  Wen-Hsiang Tsai,et al.  Moment-preserving thresolding: A new approach , 1985, Comput. Vis. Graph. Image Process..

[9]  J. M. White,et al.  Image Thresholding for Optical Character Recognition and Other Applications Requiring Character Image Extraction , 1983, IBM J. Res. Dev..

[10]  N. Otsu A threshold selection method from gray level histograms , 1979 .

[11]  Sargur N. Srihari,et al.  Document Image Binarization: Evaluation Of Algorithms , 1986, Optics & Photonics.

[12]  Sargur N. Srihari,et al.  An object attribute thresholding algorithm for document image binarization , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).