检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]中南大学信息科学与工程学院,湖南长沙410008 [2]湖南工程学院电气信息学院,湖南湘潭411101
出 处:《中南大学学报(自然科学版)》2013年第3期1043-1048,共6页Journal of Central South University:Science and Technology
基 金:湖南省教育厅科研项目(08c220)
摘 要:提出一种基于优化形式的着色框架,并构建其等效求解电路,从而把着色问题转化为电路中节点电位的求解。设计一种能调节物体间颜色过渡带宽度的改进算法,并对其着色特性与现有混色算法进行比较分析。实验结果表明:根据电路理论中的基尔霍夫电流定律,证明了现有的2种着色算法等价;优化式着色实际上是一种混色过程,其混色权重等于像素随机游走的首达概率。优化式着色算法既能获得均匀的颜色渐变特性,又可以在物体间作很好的颜色区分。A general frame for colorization based on optimization was put forward,and followed by its equivalent electrical circuit which formulates colorization process as evaluating potential of all nodes.An improved algorithm which is capable of adjusting width of transition area in between two objectives was designed.And then the colorization feature was compared with that of existing chrominance blending methods.The results indicate that it has been proved that the two existing methods are equivalent according to Kirchhoff’s current law,and the optimization-based colorization can be also viewed as that of chrominance blending where every blending weight of each pixel equals this pixel’s first-reach probability in its random walk to relevant kind of scribble.This proposed approach has provides good quality in both distinguishing from two objects and preserving homogeneous gradient colors inside.
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.175