Image registration using 2D projection transformation invariant GPT correlation
Image registration using 2D projection transformation invariant GPT correlation
复制标题
使用 2D 投影变换不变 GPT 相关性进行图像配准
DOI：
10.1117/12.2517185
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yukihiko Yamashita
中科院分区：
文献类型：
--
作者：
Toru Wakahara;Shizhi Zhang;Yukihiko Yamashita
本文描述了一种通过多尺度子窗口搜索使用失真容忍模板匹配的图像配准新方法。在这里，我们充分利用 GPT（全局投影变换）相关技术，最大化最佳二维投影变换模板和输入图像的子窗口区域之间的归一化互相关值。特别是，我们建议通过 GPT 相关性的迭代匹配过程，自适应地将子窗口区域的形状从原始矩形更改为其二维投影变换后的矩形。我们将这种算法命名为：自适应子窗口控制。在著名数据集 Graffiti 和 Boat 上进行的实验表明，与著名的基于特征点的技术（ASIFT（仿射尺度不变特征变换）和 RANSAC（随机样本一致性）的组合）相比，该方法在不同的缩放、旋转和视点下实现了远远优越的图像配准能力。
This paper describes a new method of image registration using distortion-tolerant template matching via multiscale subwindow search. Here, we make full use of the GPT (Global Projection Transformation) correlation technique that maximizes a normalized cross-correlation value between an optimally 2D projection transformed template and a subwindow area of an input image. In particular, we propose to adaptively change the shape of the subwindow area from an original rectangle to its 2D projection transformed one through iterative matching process via the GPT correlation. We name this algorithm: adaptive subwindow control. Experiments made on the well-known datasets, Graffiti and Boat, show that the proposed method achieves a far superior ability of image registration under varying zoom, rotation, and viewpoints to the well-known feature-point based technique: a combination of ASIFT (Affine Scale-Invariant Feature Transform) and RANSAC (Random Sample Consensus).