Efficient image colorization based on seed pixel selection
Efficient image colorization based on seed pixel selection
复制标题
基于种子像素选择的高效图像着色
DOI：
10.1007/s11042-016-4112-9
复制
发表时间：
2017-11
影响因子：
3.6
通讯作者：
Yi Xiao
中科院分区：
文献类型：
--
作者：
Min Hu;Bo Ou;Yi Xiao
彩色化是一种根据几种输入颜色自动生成单色图像和视频的颜色分量的技术。通常，图像彩色化是由用户指定颜色的多个种子像素初始化的，然后在给定的优化约束下，颜色逐渐按比例分配到单色环境。因此，彩色化的性能在很大程度上取决于种子像素的选择。然而，种子像素的选择却鲜有人关注，如何提高人工输入的有效性仍然是一项具有挑战性的任务。为了解决这一问题，提出了一种使用种子像素选择的改进的彩色化方法，以帮助用户确定对于高质量的彩色图像来说哪些像素是非常需要彩色化的。具体地，首先将灰度图像划分为不重叠的块，然后针对每个块，选择与块的平均亮度接近的两个像素作为种子。在用户对种子像素进行着色之后，采用最小化种子像素与其相邻像素之间的差异的优化来将颜色传播到其他像素。实验结果表明，对于给定的输入量，该方法可以获得比传统彩色化方法更高的峰值信噪比。
Colorization is a technique to automatically produce color components for monochrome images and videos based on a few input colors. Generally, image colorization is initialized from a number of seed pixels whose colors are specified by users, and then the colors are gradually prorogating to the monochrome surroundings under a given optimization constraint. So, the performance of colorization is highly dependent on the selection of seed pixels. However, little attention has been paid to the selection of seed pixels, and how to improve the effectiveness of manual input remains a challenging task. To address this, an improved colorization method using seed pixel selection is proposed to assist the users in determining which pixels are highly required to be colorized for a high-quality colorized image. Specifically, the gray-scale image is first divided into non-overlapped blocks, and then, for each block, two pixels that approximate the average luminance of block are selected as the seeds. After the seed pixels are colored by users, an optimization that minimizes the difference between the seeds and their adjacent pixels is employed to propagate the colors to the other pixels. The experimental results demonstrate that, for a given amount of inputs, the proposed method can achieve a higher PSNR than the conventional colorization methods.
登录
查看更多内容
流形保留编辑传播
影响因子：
6.2
作者：
Chen, Xiaowu;Zou, Dongqing;Tan, Ping
通讯作者：
Tan, Ping
影响因子：
10.6
作者：
Xiaowu Chen;Jianwei Li;Dongqing Zou;Qinping Zhao
通讯作者：
Xiaowu Chen;Jianwei Li;Dongqing Zou;Qinping Zhao
影响因子：
10.6
作者：
S. Lee;Sang Wook Park;Paul Oh;M. Kang
通讯作者：
S. Lee;Sang Wook Park;Paul Oh;M. Kang
DOI：
10.1137/140979368
发表时间：
2015-03
期刊：
SIAM J. Imaging Sci.
影响因子：
--
作者：
F. Pierre;Jean-François Aujol;Aurélie Bugeau;N. Papadakis;Vinh-Thong Ta
通讯作者：
F. Pierre;Jean-François Aujol;Aurélie Bugeau;N. Papadakis;Vinh-Thong Ta
DOI：
10.1109/icme.2008.4607740
发表时间：
2008-08
期刊：
2008 IEEE International Conference on Multimedia and Expo
影响因子：
--
作者：
M. Chaumont;W. Puech
通讯作者：
M. Chaumont;W. Puech