Dept. of Electr. and Comput. Eng., Illinois Univ., Urbana, IL.
IEEE Trans Image Process. 1997;6(5):642-55. doi: 10.1109/83.568922.
This paper is concerned with the detection of low-level structure in images. It describes an algorithm for image segmentation at multiple scales. The detected regions are homogeneous and surrounded by closed edge contours. Previous approaches to multiscale segmentation represent an image at different scales using a scale-space. However, structure is only represented implicitly in this representation, structures at coarser scales are inherently smoothed, and the problem of structure extraction is unaddressed. This paper argues that the issues of scale selection and structure detection cannot be treated separately. A new concept of scale is presented that represents image structures at different scales, and not the image itself. This scale is integrated into a nonlinear transform which makes structure explicit in the transformed domain. Structures that are stable (locally invariant) to changes in scale are identified as being perceptually relevant. The transform can be viewed as collecting spatially distributed evidence for edges and regions, and making it available at contour locations, thereby facilitating integrated detection of edges and regions without restrictive models of geometry or homogeneity. In this sense, it performs Gestalt analysis. All scale parameters of the transform are automatically determined, and the structure of any arbitrary geometry can be identified without any smoothing, even at coarse scales.
本文关注的是图像中低水平结构的检测。它描述了一种多尺度图像分割算法。检测到的区域是均匀的，并且被封闭的边缘轮廓包围。以前的多尺度分割方法使用尺度空间来表示不同尺度的图像。然而，这种表示中只隐含地表示了结构，较粗糙尺度上的结构被固有地平滑化，并且结构提取的问题未得到解决。本文认为，尺度选择和结构检测的问题不能分开处理。提出了一种新的尺度概念，它表示不同尺度的图像结构，而不是图像本身。这个尺度被集成到一个非线性变换中，使结构在变换域中变得明显。在尺度变化下稳定（局部不变）的结构被识别为具有感知相关性。该变换可以看作是在边缘和区域的位置收集空间分布的证据，从而在不需要几何形状或均匀性的限制性模型的情况下，方便地进行边缘和区域的集成检测。从这个意义上说，它执行了格式塔分析。变换的所有尺度参数都是自动确定的，并且可以识别任何任意几何形状的结构，而无需任何平滑处理，即使在粗糙尺度上也是如此。
