摘要
针对传统织物图像色彩转移方法中存在的算法复杂度高、不能很好地保留原织物图像的层次感和细节等问题,文中结合显著颜色提取提出了一种新的织物图像色彩转移改进方法。一方面,利用显著颜色提取得到原织物图像更具代表性的主要颜色和分割区域,以使色彩转移结果图像的层次感更加忠实于原织物图像。另一方面,利用图像分解和一种简单高效的防溢出色彩转移策略更好地保持了色彩转移结果图像的细节。仿真实验结果表明,相对于传统的织物图像色彩转移方法,文中所提新方法不仅能够有效地保持原织物图像的层次感和细节,而且运行效率也得到了明显的提高。新方法具有简单、高效的特点,能够较好地适用于织物图像的颜色设计工作。
Since there are the low-efficiency preservation of the layering and details of the original fabric image, and the high-complexity algorithm in the traditional fabric image color transfer method, an improved fabric image color transfer method with significant color extraction is proposed in this paper. By employing the significant color extraction, more representative main colors and segmentation regions of the original fabric image are obtained to make the layering of the resulting image more faithful to the original fabric image. In addition, image details of the resulting image are better preserved by using the image decomposition and anti-overflow color transfer strategy. The simulation results show that, compared with the traditional fabric image color transfer method, the newly proposed method can not only effectively maintain the layering and details of the original fabric image, but also significantly improve the operation efficiency. The newly proposed method is simple and efficient, and can be better applied to the color design work of fabric images.
引文
[1] Yang Y,Zhao H,You L,et al.Semantic portrait color transfer with internet images[J].Multimedia Tools and Applications,2017,76(1):523-541.
[2] Gu X,He M,Gu X.Thermal image colorization using Markov decision processes[J].Memetic Computing,2016,9(1):15-22.
[3] Xie B,Xu C,Han Y,et al.Color transfer using adaptive second-order total generalized variation regularizer[J].IEEE Access,2018,6(3):6829- 6839.
[4] Yang C N,Tung T C,Wu F H,et al.Color transfer visual cryptography with perfect security[J].Measurement,2017,9(5):480- 493.
[5] Reinhard E,Adhikhmin M,Gooch B,et al.Color transfer between images[J].IEEE Computer Graphics and Applications,2001,21(5):34- 41.
[6] Liu S G,Pei M.Texture-aware emotional color transfer between images[J].IEEE Access,2018,6(6):31375-31386.
[7] Liu T,Wei Y,Zhao Y,et al.Magic-wall:Visualizing room decoration[C]//Proc.of ACM International Conference on Multimedia,2017:429- 437.
[8] Wen C L,Hsieh C H,Chen B Y,et al.Example-based multiple local color transfer by strokes[J].Computer Graphics Forum,2008,27(7):1765-1772.
[9] Chang H,Fried O,Liu Y,et al.Palette-based photo recol-oring[J].Acm Transactions on Graphics,2015,34(4):1-11.
[10] Ou L C,Luo M R,Woodcock A,et al.A study of color emotion and color preference[J].Color Research & Application,2004,29(3):232-240.
[11] Solli M,Lenz R.Color emotions for multi-colored images[J].Color Research & Application,2011,36(3):210-221.
[12] Han Y,Zheng D J,Baciu G,et al.Fuzzy region competition-based auto-color-theme design for textile images[J].Textile Research Journal,2013,83(6):638- 650.
[13] 张智勇,常侃,陈诚,等.应用残差总变分及低秩表示的视频去噪算法[J].信号处理,2016,32(5):558-566.Zhang Zhiyong,Chang Kan,Chen Cheng,et al.A video denoising algorithm using residual total variation and low-rank representation[J].Journal of Signal Processing,2016,32(5):558-566.(in Chinese)
[14] Li F,Ng M K,Zeng T Y,et al.A multiphase image seg-mentation method based on fuzzy region competition[J].Siam Journal on Imaging Sciences,2010,3(3):277-299.
[15] Han Y,Xu C,Baciu G,et al.Cartoon and texture decomposition based color transfer for fabric images[J].IEEE Transactions on Multimedia.2017,19(1):80-92.
[16] Ng M K,Yuan X,Zhang W.Coupled variational image decomposition and restoration model for blurred cartoon-plus-texture images with missing pixels[J].IEEE Transactions on Image Processing,2013,22(6):2233-2246.