Paper available: An improved Neural Network based Edge Detection method

[Md. Shoaib Bhuiyan]

The following paper is available for copying. It was published in
Proceedings of Int'l. Conf. on Neural Information Processing, Seoul,
Korea, vol. 1, pp.620-625, Oct. 17-20, 1994.


        An improved Neural Network based Edge Detection method


Abstract: Existing edge detection methods provide unsatisfactory
        results when contrast changes largely within an image due to
        non-uniform illumination.  Koch et al. developed an energy
        function based upon Hopfield neural network, whose coefficients were
	fixed by trial and error and remains constant for the entire image,
	irrespective of the differences in intensity level. This paper
	presents an improved edge detection method for images where contrast
	is not uniform. we propose that the energy function parameters for an
	image with inconsistent illumination should not remain fixed and
	propose an schedule to change these parameters. The results,
	compared with those of existing one's, suggest a better strategy for
	edge detection depending upon both the dynamic range of the original
	image pixel values as well as their contrast.


-----------------------------------------------------------------

The paper can be retrieved via anonymous ftp by following these
instructions:

        unix>      ftp ftp.elcom.nitech.ac.jp
        ftp:name>  anonymous
        Password:> your complete e-mail address
        ftp>       cd pub
        ftp>       get ICONIP.ps.gz
        ftp>       bye
        unix>      gunzip ICONIP.ps.gz
        unix>      lpr ICONIP.ps

ICONIP.ps is 3.58Mb, six pages in postscript format. The paper proposes
a novel idea to extract edges from an image with high contrast. Your
feedback is very much appreciated (bhuiyan at mars.elcom.nitech.ac.jp)

-Md. Shoaib Bhuiyan