Back to articles
Volume: 28 | Article ID: art00037
Digital Image Segmentation for Object-Oriented Halftoning
  DOI :  10.2352/ISSN.2470-1173.2016.20.COLOR-350  Published OnlineFebruary 2016

The electrophotographic (EP) process, which is widely used in imaging systems such as laser printers, is susceptible to printing artifacts if we render the smooth areas of the images with high frequency halftone screens. However, applying low frequency halftone screens over the whole page will restrict the ability to render the fine details [1]. The solution proposed by Park [2] et al is to apply different frequency screens to different parts of the page – also referred to as object-oriented halftoning. But it requires a correct object map to be generated. With miscellaneous segmented objects in a given image, an object map will classify all the image objects into three categories: raster (pictures or photos), vector (background and gradient) and symbol (symbols and texts), with raster and symbol objects considered as high frequency objects and vector objects as low frequency objects. An overall improvement of the print quality can be achieved if symbol and raster objects are rendered with high frequency, and vector objects with low frequency. Although the object map can be extracted from the page description language (PDL) directly, some components may not be correctly classified [1]. To obtain a correct object map from the page image, not the PDL, an object map generating algorithm is proposed in this paper. The algorithm uses a strip-based processing, which only requires a strip of the image to be buffered. And it is very memory efficient, making it ideal for hardware implementation.

Subject Areas :
Views 12
Downloads 0
 articleview.views 12
 articleview.downloads 0
  Cite this article 

Zuguang Xiao, Mengqi Gao, Lu Wang, Brent Bradburn, Jan Allebach, "Digital Image Segmentation for Object-Oriented Halftoningin Proc. IS&T Int’l. Symp. on Electronic Imaging: Color Imaging XXI: Displaying, Processing, Hardcopy, and Applications,  2016,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
Electronic Imaging
Society for Imaging Science and Technology