图像处理-尺度空间理论

本文简要介绍尺度空间理论。如果你对这个理论是如何提出、发展的，可以详细地阅读相关文献，见参考文献。

简单地说，尺度空间理论（scale-space theory）的提出主要是为了解决如何识别不同大小物体的问题。通过将一系列不同“大小”的高斯滤波器$G(x,y;t)$与原始图像$I(x,y)$进行卷积，获得不同分辨率的图像$L(x,y;t)$。

对于二维图像$I(x,y)$在不同尺度$t$下的图像，$$L(x,y;t)=G(x,y;t)\ast I(x,y)$$

其中,$$G(x,y;t)=\frac{1}{2\pi t}{e}^{-(x^2+y^2)/2t}$$

由卷积的微分性质，可以得到

$$L(x,y;t{)}_{xx}=\frac{{\partial }^2(G(x,y;t)\ast I(x,y))}{{\partial }^{2}x}=\frac{{\partial }^{2}G(x,y;t)}{{\partial }^{2}x}\ast I(x,y)$$

$$L(x,y;t{)}_{yy}=\frac{{\partial }^2(G(x,y;t)\ast I(x,y))}{{\partial }^{2}y}=\frac{{\partial }^{2}G(x,y;t)}{{\partial }^{2}y}\ast I(x,y)$$

$$L(x,y;t{)}_{xy}=\frac{{\partial }^2(G(x,y;t)\ast I(x,y))}{\partial x\partial y}=\frac{{\partial }^{2}G(x,y;t)}{\partial x\partial y}\ast I(x,y)$$

因此，图像的Hessian矩阵为
$$H(x,y)=\left[\begin{array}{cc}\frac{{\partial }^{2}G(x,y;t)}{{\partial }^{2}x}& \frac{{\partial }^{2}G(x,y;t)}{\partial x\partial y}\\ \frac{{\partial }^{2}G(x,y;t)}{\partial x\partial y}& \frac{{\partial }^{2}G(x,y;t)}{{\partial }^{2}y}\end{array}\right]\ast I(x,y)$$

---

参考文献

• 1996, Lindeberg Tony, Scale-space: A framework for handling image structures at multiple scales
• 2000, Krissian Karl, Model Based Detection of Tubular Structures in 3D Images
• 2009, Marcin Rudzki, Vessel Detection Method Based on Eigenvalues of the Hessian Matrix and its Applicability to Airway Tree Segmentation