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 the Hopfield neural network, whose coefficients were fixed by trial and error, and remain constant for the entire image, irrespective of the differences in intensity level. This paper presents an improved edge detection method for non-uniformly illuminated images. We propose that the energy function coefficients for an image with inconsistent illumination should not remain fixed, rather should vary as a second-order function of the intensity differences between pixels, and actually use a schedule of changing coefficients. The results, compared with those of existing methods, 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 copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Md. Shoaib BHUIYAN, Hiroshi MATSUO, Akira IWATA, Hideo FUJIMOTO, Makoto SATOH, "Edge Detection Using Neural Network for Non-uniformly Illuminated Images" in IEICE TRANSACTIONS on Information,
vol. E79-D, no. 2, pp. 150-160, February 1996, doi: .
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 the Hopfield neural network, whose coefficients were fixed by trial and error, and remain constant for the entire image, irrespective of the differences in intensity level. This paper presents an improved edge detection method for non-uniformly illuminated images. We propose that the energy function coefficients for an image with inconsistent illumination should not remain fixed, rather should vary as a second-order function of the intensity differences between pixels, and actually use a schedule of changing coefficients. The results, compared with those of existing methods, suggest a better strategy for edge detection depending upon both the dynamic range of the original image pixel values as well as their contrast.
URL: https://global.ieice.org/en_transactions/information/10.1587/e79-d_2_150/_p
Copy
@ARTICLE{e79-d_2_150,
author={Md. Shoaib BHUIYAN, Hiroshi MATSUO, Akira IWATA, Hideo FUJIMOTO, Makoto SATOH, },
journal={IEICE TRANSACTIONS on Information},
title={Edge Detection Using Neural Network for Non-uniformly Illuminated Images},
year={1996},
volume={E79-D},
number={2},
pages={150-160},
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 the Hopfield neural network, whose coefficients were fixed by trial and error, and remain constant for the entire image, irrespective of the differences in intensity level. This paper presents an improved edge detection method for non-uniformly illuminated images. We propose that the energy function coefficients for an image with inconsistent illumination should not remain fixed, rather should vary as a second-order function of the intensity differences between pixels, and actually use a schedule of changing coefficients. The results, compared with those of existing methods, suggest a better strategy for edge detection depending upon both the dynamic range of the original image pixel values as well as their contrast.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - Edge Detection Using Neural Network for Non-uniformly Illuminated Images
T2 - IEICE TRANSACTIONS on Information
SP - 150
EP - 160
AU - Md. Shoaib BHUIYAN
AU - Hiroshi MATSUO
AU - Akira IWATA
AU - Hideo FUJIMOTO
AU - Makoto SATOH
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E79-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 1996
AB - 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 the Hopfield neural network, whose coefficients were fixed by trial and error, and remain constant for the entire image, irrespective of the differences in intensity level. This paper presents an improved edge detection method for non-uniformly illuminated images. We propose that the energy function coefficients for an image with inconsistent illumination should not remain fixed, rather should vary as a second-order function of the intensity differences between pixels, and actually use a schedule of changing coefficients. The results, compared with those of existing methods, suggest a better strategy for edge detection depending upon both the dynamic range of the original image pixel values as well as their contrast.
ER -