Frontiers of Information Technology & Electronic Engineering
>> 2017,
Volume 18,
Issue 11
doi:
10.1631/FITEE.1600017
Article
A two-stage parametric subspace model for efficient contrast-preserving decolorization
. Department of Electronic Information Engineering, Nanchang University, Nanchang 330031, China.. Institute of Space Science and Technology, Nanchang University, Nanchang 330031, China.
Available online: 2018-03-08
Next
Previous
Abstract
The RGB2GRAY conversion model is the most popular and classical tool for image decolorization. A recent study showed that adapting the three weighting parameters in this first-order linear model with a discrete searching solver has a great potential in its conversion ability. In this paper, we present a two-step strategy to efficiently extend the parameter searching solver to a two-order multivariance polynomial model, as a sum of three subspaces. We show that the first subspace in the two-order model is the most important and the second one can be seen as a refinement. In the first stage of our model, the gradient correlation similarity (Gcs) measure is used on the first subspace to obtain an immediate grayed image. Then, Gcs is applied again to select the optimal result from the immediate grayed image plus the second subspace-induced candidate images. Experimental results show the advantages of the proposed approach in terms of quantitative evaluation, qualitative evaluation, and algorithm complexity.
京公网安备 11010502051620号
