Multiple-content Image Colorization Algorithm Based on Classified Dictionary
-
摘要: 为解决基于字典学习与稀疏表示的灰度图像彩色化算法只对单一内容图像有效这一问题,提出了一种新型的图像彩色化方法.首先,根据目标灰度图像的子内容分别选取多组参考彩色图像,从各组参考彩色图像中选取对应子内容的样本图像块;然后,分别进行字典训练,得到基于内容的分类字典;最后,根据重建误差最小化原则,查找最佳匹配字典,进而实现灰度图像的彩色化.该算法是一种自动算法,在保证图像彩色化过程自动化的前提下,提高了彩色化效果.实验结果表明:该算法能够对目标灰度图像中的不同内容分别进行正确彩色化处理.Abstract: A novel method of image colorization is proposed. It overcomes the problem existed in algorithm of image colorization based on dictionary learning and sparse representation. First,multiple blocks from reference color images was selected according to the sub-contents of target gray-scale image.Second,the multiple blocks are trained respectively to obtain classified dictionaries based on contents.Finally,the best matching sub-dictionary can be decided by minimizing the reconstruction error and the gray-scale image is colorized. This algorithm was automatic and the performance of colorization was improved on the premise of guaranteeing the automation of the image colorization process. Experimental results show that the algorithm is able to colorize the target gray-scale images of different contents automatically.
-
-
[1] LIRON Y,GUILLERMO S.Fast image and video colorization using chrominance blending[J].IEEE Transcations on Image Processing,2006,15(5):1120-1129.
[2] HORIUCHI T.Estimation of color for gray-level Image by probabilistic relaxation[C]∥ICPR 2002 Proceedings of the 16th International Conference on Pattern Recogni-tion.Washington,DC:IEEE Computer Socitey,2002:867-870.
[3] LEVIN A,LISCHINSKI D,WEISS Y.Colorization using optimization[C]∥Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH.New York:ACM,2004:689-694.
[4] WELSH T,ASHIKHMIN M,MUELLER K.Transferring color to greyscale images[C]∥Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH.New York:ACM,2002:277-280.
[5] MAIRAL J,ELAD M,SAPIRO G.Sparse representation for color image restoration[J].IEEE Transcations on Image Processing,2008,17(1):53-69.
[6] DONOHO D L.Compressed sensing[J].IEEE Transcations on Information Theory,2006,52(4):1289-1306.
[7] 张勋,赵瑞珍,岑翼刚,等.基于字典学习与稀疏表示的灰度图像颜色重建算法[J].计算机辅助设计与图形学学报,2014,26(7):1092-1098.ZHANG X,ZHAO R Z,CEN Y G,et al.Color reconstruction algorithm for grayscale images based on dictionary learning and sparse representation[J].Journal of Computer-Aided Design&Computer Graphics,2014,26(7):1092-1098.(in Chinese) [8] 郝凯,宋明黎,卜佳俊,等.局部稀疏编码的自然灰度图像着色方法[J].计算机辅助设计与图形学学报,2011,23(8):1401-1408.HAO K,SONG M L,BU J J,et al.Natural grayscale image colorization via local sparse coding[J].Journal of Computer-Aided Design&Computer Graphics,2011,23(8):1401-1408.(in Chinese) [9] PANG J H,AU O C,TANG K T,et al.Image colorization using sparse representation acoustics[C]∥Speech and Signal Processing,IEEE International Conference on.Piscataway,NJ:IEEE,2013:1578-1582.
[10] TROOP J A,GILBERT A C.Signal recovery from random measurements via orthogonal matching pursuit[J].IEEE Transactions on Information Theory,2007,53(12):4655-4666.
[11] AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transsactions on Signal Processing,2006,54(11):4311-4322.
[12] GAO S,TSANG I,MA Y.Learning category-specific dictionary and shared dictionary for fine-grained image gategorization[J].IEEE Transactions on Image Processing,2014,23(2):623-634.
[13] 吕东辉,张闯,汪世刚.利用图像块数据库和纹理特征点的图像彩色化方法[J].上海大学学报,2011,17(1):57-63.LD H,ZHANG C,WANG S G.Image colorization with block image database and texture feature points[J].Journal of Shanghai University,2011,17(1):57-63.(in Chinese)
计量
- 文章访问数: 21
- HTML全文浏览量: 1
- PDF下载量: 9
下载:
