Color Image Enhancement Using Human Visual Properties and Neural Network


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 5, No. 12, pp. 3265-3274, Dec. 1998
10.3745/KIPSTE.1998.5.12.3265,   PDF Download:

Abstract

In this paper, we proposes a new color enhancement method that enhances the saturations of a degraded image using the neural network which is learned by the relations among intensities, saturations, and hues. In the proposed method, the neural network is learned: the input is intensities, saturations, and hues which is derived from the standard image into a various degraded image and the desired target is the saturation of the standard image. Intensity, saturation, and hue of a degraded image and enhanced intensity are inputted in the learned neural network, then we obtain the enhanced saturation. We show this method solves color gamut problem that is serious problem in the previous method, and that this method enhances the contrast of saturation, then, makes a vivid image obtained.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. H. Wook and C. S. Jae, "Color Image Enhancement Using Human Visual Properties and Neural Network," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 5, no. 12, pp. 3265-3274, 1998. DOI: 10.3745/KIPSTE.1998.5.12.3265.

[ACM Style]
Shin Hyun Wook and Cho Seok Jae. 1998. Color Image Enhancement Using Human Visual Properties and Neural Network. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 5, 12, (1998), 3265-3274. DOI: 10.3745/KIPSTE.1998.5.12.3265.