1 April 1997 Extracting halftones from printed documents using texture analysis
Author Affiliations +
Separating halftones from text is an important step in document analysis. We present an algorithm that accurately extracts halftones from other information in printed documents. We treat halftone extraction as a texture-segmentation problem. We show that commonly used halftones, consisting of a pattern of dots, can be viewed as a texture. This texture exhibits a distinct spectral component that can be detected using a properly tuned Gabor filter. The Gabor filter essentially transforms halftones into high-contrast regions that can be easily segmented by thresholding. We propose a filter design procedure and provide experimental results.
Dennis F. Dunn, Dennis F. Dunn, Thomas P. Weldon, Thomas P. Weldon, William E. Higgins, William E. Higgins, } "Extracting halftones from printed documents using texture analysis," Optical Engineering 36(4), (1 April 1997). https://doi.org/10.1117/1.601289 . Submission:

Back to Top