CLC number: TM346
On-line Access: 2018-01-12
Received: 2016-01-12
Revision Accepted: 2016-05-22
Crosschecked: 2017-11-26
Cited: 0
Clicked: 6537
Hong-yang Lu, Qie-gen Liu, Yu-hao Wang, Xiao-hua Deng. A two-stage parametric subspace model for efficient contrast-preserving decolorization[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(11): 1874-1882.
@article{title="A two-stage parametric subspace model for efficient contrast-preserving decolorization",
author="Hong-yang Lu, Qie-gen Liu, Yu-hao Wang, Xiao-hua Deng",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="18",
number="11",
pages="1874-1882",
year="2017",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1600017"
}
%0 Journal Article
%T A two-stage parametric subspace model for efficient contrast-preserving decolorization
%A Hong-yang Lu
%A Qie-gen Liu
%A Yu-hao Wang
%A Xiao-hua Deng
%J Frontiers of Information Technology & Electronic Engineering
%V 18
%N 11
%P 1874-1882
%@ 2095-9184
%D 2017
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1600017
TY - JOUR
T1 - A two-stage parametric subspace model for efficient contrast-preserving decolorization
A1 - Hong-yang Lu
A1 - Qie-gen Liu
A1 - Yu-hao Wang
A1 - Xiao-hua Deng
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 18
IS - 11
SP - 1874
EP - 1882
%@ 2095-9184
Y1 - 2017
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1600017
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.
[1]Ancuti, C.O., Ancuti, C., Hermans, C., et al., 2010. Image and video decolorization by fusion. Asian Conf. on Computer Vision, p.79-92.
[2]Ancuti, C.O., Ancuti, C., Bekaert, P., 2011. Enhancing by saliency-guided decolorization. IEEE Conf. on Computer Vision and Pattern Recognition, p.257-264.
[3]Bala, R., Eschbach, R., 2004. Spatial color-to-grayscale transform preserving chrominance edge information. 12th Color and Imaging Conf., p.82-86.
[4]Ĉadík, M., 2008. Perceptual evaluation of color-to-grayscale image conversions. Comput. Graph. Forum, 27(7):1745-1754.
[5]Chan, S.H., Khoshabeh, R., Gibson, K.B., et al., 2011. An augmented Lagrangian method for total variation video restoration. IEEE Trans. Imag. Process., 20(11):3097-3111.
[6]Du, H., He, S., Sheng, B., et al., 2015. Saliency-guided color-to-gray conversion using region-based optimization. IEEE Trans. Imag. Process., 24(1):434-443.
[7]Gooch, A.A., Olsen, S.C., Tumblin, J., et al., 2005. Color2gray: salience-preserving color removal. ACM Trans. Graph., 24(3):634-639.
[8]Grundland, M., Dodgson, N.A., 2007. Decolorize: fast, contrast enhancing, color to grayscale conversion. Patt. Recogn., 40(11):2891-2896.
[9]Jin, Z., Li, F., Ng, M.K., 2014. A variational approach for image decolorization by variance maximization. SIAM J. Imag. Sci., 7(2):944-968.
[10]Kim, Y., Jang, C., Demouth, J., et al., 2009. Robust color-to-gray via nonlinear global mapping. ACM Trans. Graph., 28(5):1-4.
[11]Kuk, J.G., Ahn, J.H., Cho, N.I., 2010. A color to grayscale conversion considering local and global contrast. Asian Conf. on Computer Vision, p.513-524.
[12]Liu, Q., Liu, P.X., Xie, W., et al., 2015. GcsDecolor: gradient correlation similarity for efficient contrast preserving decolorization. IEEE Trans. Imag. Process., 24(9): 2889-2904.
[13]Lu, C., Xu, L., Jia, J., 2012a. Contrast preserving decolorization. IEEE Int. Conf. on. Computational Photography, p.1-7.
[14]Lu, C., Xu, L., Jia, J., 2012b. Real-time contrast preserving decolorization. ACM SIGGRAPH Asia Technical Briefs, Article 34.
[15]Neumann, L., Čadík, M., Nemcsics, A., 2007. An efficient perception-based adaptive color to gray transformation. Proc. 3rd Eurographics Conf. on Computational Aesthetics in Graphics, Visualization and Imaging, p.73-80.
[16]Rasche, K., Geist, R., Westall, J., 2005. Re-coloring images for gamuts of lower dimension. Comput. Graph. Forum, 24(3):423-432.
[17]Smith, K., Landes, P.E., Thollot, J., et al., 2008. Apparent greyscale: a simple and fast conversion to perceptually accurate images and video. Comput. Graph. Forum, 27(2):193-200.
[18]Song, Y., Bao, L., Xu, X., et al., 2013. Decolorization: is rgb2gray() out ACM SIGGRAPH Asia Technical Briefs, Article 15.
[19]Wang, J.G., Yau, W.Y., 2014. Real-time moustache detection by combining image decolorization and texture detection with applications to facial gender recognition. Mach. Vis. Appl., 25(4):1089-1099.
[20]Wang, Z., Bovik, A.C., Sheikh, H.R., et al., 2004. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Imag. Process., 13(4):600-612.
Open peer comments: Debate/Discuss/Question/Opinion
<1>