Abstract
This paper proposes a new objective distortion measure for binary document images. This measure is based on flipped pixel’s immediate neighbors. And it considers the distance between the flipped pixel and neighbor pixels and stroke direction of the neighbor pixels. The simulation and experiments results show that the proposed distortion measure for binary document images matches well to subjective evaluation by human visual perception.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Yun, Q.S., Huifang, S.: Image and Video Compression for Multimedia Engineering: Fundamental, Algorithm, and Standards. CRC Press, Boca Raton (1999)
Min, W., Bede, L.: Data hiding in digital binary image. In: Proc. IEEE Int. Conference on Multimedia and Expo, New York City, July 31-August 2, vol. 1, pp. 393–396 (2000)
Haiping, L., Jian, W., Alex, C.K., Yun, Q.S.: An objective distortion measure for binary document images based on human visual perception. In: Proceeding International Conference Pattern Recognition, Quebec, Canada, August 2002, vol. 4, pp. 239–242 (2002)
Taylor, M.M.: Visual Discrimination and Orientation. Journal of the Optical Society of America A, 763–765 (1963)
Milan, S., Vaclav, H., Roger, B.: Image Processing, Analysis, and Machine Vision. Thomson-Engineering, 2nd edn. (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jin, G., Lee, K.D. (2005). Distortion Measure for Binary Document Image Using Distance and Stroke. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2005. ICCSA 2005. Lecture Notes in Computer Science, vol 3483. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11424925_114
Download citation
DOI: https://doi.org/10.1007/11424925_114
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25863-6
Online ISBN: 978-3-540-32309-9
eBook Packages: Computer ScienceComputer Science (R0)