一种高效的灰度图像真彩化方案  

Efficient colorization scheme for grayscale image

作　　者：王文锦[1] 丁浩[1] 陆平[1] 赵书国[1] 贾世奎[1] 

机构地区：[1]中国船舶重工集团公司第七一八研究所,河北邯郸056000

出　　处：《激光与红外》2012年第2期205-208,共4页Laser & Infrared

摘　　要：提出了一种高效的灰度图像真彩化方案。该方案的关键技术包括:YUV亮色分离、采样点序列去冗余精简和基于像素空间相关性的匹配点搜索。YUV亮色分离技术在复杂度低、计算量小的同时,有效去除了RGB颜色空间中存在的相关性。通过去除采样点序列的数据冗余,节省了后续整幅目标图像的匹配点搜索时间。利用图像像素点的空间相关性进行匹配点搜索,提高了搜索效率和准确性。经实验验证,本文算法在取得和Welsh算法相近效果的同时,可以节省50%～70%的彩色化处理时间。This paper presents an efficient grayscale image colorization scheme that mainly consists of three components including YUV-transformation,sample sequence redundancy removal and space relativity based pixel matching.The low-complexity YUV-transformation technique can effectively remove the correlation existing in RGB color space.A sample sequence redundancy removal strategy is proposed to cut down the pixel matching time of the whole target image.A space relativity based pixel matching algorithm is employed to improve searching efficiency and accuracy.The experimental results show that while obtaining results similar to Welsh algorithm′s performance,the proposed efficient grayscale image colorization scheme can save time from 50% to 70% for the colorization process.

关 键 词：图像真彩化 YUV亮色分离 采样点去冗余 匹配点搜索 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]