为提高复杂图像受损区域的纹理和结构信息的修复效果,使其更加符合人眼的视觉要求,提出一种改进的Criminisi算法,通过改进优先权函数、优先顺序判断准则和匹配准则使修复效果更好。对数据项和置信项加入正则化因子,将优先权函数变为加...为提高复杂图像受损区域的纹理和结构信息的修复效果,使其更加符合人眼的视觉要求,提出一种改进的Criminisi算法,通过改进优先权函数、优先顺序判断准则和匹配准则使修复效果更好。对数据项和置信项加入正则化因子,将优先权函数变为加权求和的形式;在优先权相等的情况下,继续使用数据项进行优先修复像素点的选择,使其优先修复结构信息丰富的破损区域;在匹配准则方面,在欧式距离颜色分量差值平方和(sum of squared difference,SSD)的匹配准则下,对于SSD相等的情况,继续用方差误差(Var_error)和物理距离(Dis)匹配方式进行判断,选择最佳匹配像素块。实验结果表明,该算法能够获得更佳的修复效果,结构边缘部分能够得到更好的修复。展开更多
Metal matrix composites reinforced with graphite particles provide better machinability and tribological properties. The present study attempts to find the optimal level of machining parameters for multi-performance c...Metal matrix composites reinforced with graphite particles provide better machinability and tribological properties. The present study attempts to find the optimal level of machining parameters for multi-performance characteristics in turning of Al-SiC-Gr hybrid composites using grey-fuzzy algorithm. The hybrid composites with 5%, 7.5% and 10% combined equal mass fraction of SiC-Gr particles were used for the study and their corresponding tensile strength values are 170, 210, 204 MPa respectively. Al-10%（SiC-Gr） hybrid composite provides better machinability when compared with composites with 5% and 7.5% of SiC-Gr. Grey-fuzzy logic approach offers improved grey-fuzzy reasoning grade and has less uncertainties in the output when compared with grey relational technique. The confirmatory test reveals an increase in grey-fuzzy reasoning grade from 0.619 to 0.891, which substantiates the improvement in multi-performance characteristics at the optimal level of process parameters setting.展开更多
文摘为提高复杂图像受损区域的纹理和结构信息的修复效果,使其更加符合人眼的视觉要求,提出一种改进的Criminisi算法,通过改进优先权函数、优先顺序判断准则和匹配准则使修复效果更好。对数据项和置信项加入正则化因子,将优先权函数变为加权求和的形式;在优先权相等的情况下,继续使用数据项进行优先修复像素点的选择,使其优先修复结构信息丰富的破损区域;在匹配准则方面,在欧式距离颜色分量差值平方和(sum of squared difference,SSD)的匹配准则下,对于SSD相等的情况,继续用方差误差(Var_error)和物理距离(Dis)匹配方式进行判断,选择最佳匹配像素块。实验结果表明,该算法能够获得更佳的修复效果,结构边缘部分能够得到更好的修复。
文摘Metal matrix composites reinforced with graphite particles provide better machinability and tribological properties. The present study attempts to find the optimal level of machining parameters for multi-performance characteristics in turning of Al-SiC-Gr hybrid composites using grey-fuzzy algorithm. The hybrid composites with 5%, 7.5% and 10% combined equal mass fraction of SiC-Gr particles were used for the study and their corresponding tensile strength values are 170, 210, 204 MPa respectively. Al-10%（SiC-Gr） hybrid composite provides better machinability when compared with composites with 5% and 7.5% of SiC-Gr. Grey-fuzzy logic approach offers improved grey-fuzzy reasoning grade and has less uncertainties in the output when compared with grey relational technique. The confirmatory test reveals an increase in grey-fuzzy reasoning grade from 0.619 to 0.891, which substantiates the improvement in multi-performance characteristics at the optimal level of process parameters setting.
