摘要
针对图像配准容易产生误配准、漏配准的问题,提出了基于改进尺度不变特征的图像局域几何配准。该方法改进了尺度不变特征,通过构建边缘尺度空间设计了尺度不变边缘特征变换,融合了尺度不变特征点和尺度不变边缘。以尺度不变特征为基础,搜寻图像间的局域图像变换,实现图像局域几何配准。实验表明,SIFT特征点和边缘信息互补能够提供更多的配准信息并减少错误配准;该方法对尺度、噪声、形变、光照等不敏感,能够配准移动目标,真实地反映图像的配准状况。
Aiming at the problems that the existing image registrations may trigger inaccurate registrations or miss some registrations, an image local geometric registration based on improved scale invariant features was proposed. The approach improves scale invariant features, designs SI（E） FT （scale invariant edge feature transform） by constructing edge scale space and combines scale invariant feature points and scale invariant edges. Based on the improved scale in- variant features, the local transforms between two images are searched to implement image local geometric registration. Experiments show that the complementary combination of SIFT points and edges provides more registration information and reduces registration errors,and the approach is insensitive to scale, noise, deformation, light, etc. , can register moving objects and truly reflects image registration status.
出处
《计算机科学》
CSCD
北大核心
2014年第1期111-115,共5页
Computer Science
基金
国家重点基础研究发展计划(973)项目(2013CB329502)
国家自然科学基金(41074003,51104157)资助
关键词
尺度不变边缘特征变换
尺度不变特征变换
图像变换
局域几何配准
Scale invariant edge feature transform, Scale invariant feature transform, Image transform, Local geometric registration
