更改

{{Main article|Scale space}}

{{Main article|Scale space}}

In [[computer vision]] and [[biological vision]], scaling transformations arise because of the perspective image mapping and because of objects having different physical size in the world. In these areas, scale invariance refers to local image descriptors or visual representations of the image data that remain invariant when the local scale in the image domain is changed.<ref name=Lin13PONE>[https://dx.doi.org/10.1371/journal.pone.0066990 Lindeberg, T. (2013) Invariance of visual operations at the level of receptive fields, PLoS ONE 8(7):e66990.]</ref>   

In [[computer vision]] and [[biological vision]], scaling transformations arise because of the perspective image mapping and because of objects having different physical size in the world. In these areas, scale invariance refers to local image descriptors or visual representations of the image data that remain invariant when the local scale in the image domain is changed.<ref name=Lin13PONE>[https://dx.doi.org/10.1371/journal.pone.0066990 Lindeberg, T. (2013) Invariance of visual operations at the level of receptive fields, PLoS ONE 8(7):e66990.]</ref>   

Detecting local maxima over scales of normalized derivative responses provides a general framework for obtaining scale invariance from image data.<ref name=Lindeberg1998>{{cite journal

Detecting local maxima over scales of normalized derivative responses provides a general framework for obtaining scale invariance from image data.<ref name="Lindeberg1998">Lindeberg, Tony (1998). "Feature detection with automatic scale selection". ''International Journal of Computer Vision''. '''30''' (2): 79–116. doi:10.1023/A:1008045108935. S2CID 723210.</ref><ref name=Lin14CompVis>T. Lindeberg (2014) [http://www.csc.kth.se/~tony/abstracts/Lin14-ScSel-CompVisRefGuide.html "Scale selection", Computer Vision: A Reference Guide, (K. Ikeuchi, Editor), Springer, pages 701-713.]</ref>

| author = Lindeberg, Tony

| year = 1998

| title = Feature detection with automatic scale selection

| journal = International Journal of Computer Vision

| volume = 30

| issue = 2

| pages = 79–116

| doi = 10.1023/A:1008045108935

| s2cid = 723210

| url = http://www.nada.kth.se/cvap/abstracts/cvap198.html

}}</ref><ref name=Lin14CompVis>T. Lindeberg (2014) [http://www.csc.kth.se/~tony/abstracts/Lin14-ScSel-CompVisRefGuide.html "Scale selection", Computer Vision: A Reference Guide, (K. Ikeuchi, Editor), Springer, pages 701-713.]</ref>

Examples of applications include [[blob detection]], [[corner detection]], [[ridge detection]], and object recognition via the [[scale-invariant feature transform]].

Examples of applications include [[blob detection]], [[corner detection]], [[ridge detection]], and object recognition via the [[scale-invariant feature transform]].

在计算机视觉和生物视觉中，由于图像的透视映射和世界上物体的物理尺寸不同而产生了标度变换。在这些领域中，标度不变性是指当图像域的局部尺度发生变化时，图像数据的图像描述或视觉表达效果保持不变。在归一化导数响应的尺度上检测局部极大值为从图像数据中获取标度不变性提供了一个通用框架。应用的例子包括'''Blob Detection 斑点检测'''、'''Corner Detection 角点检测、Ridge Detection 脊线检测'''和通过'''Scale-Invariant Feature Transform 标度不变特征变换'''进行的目标识别。

在计算机视觉和生物视觉中，由于图像的透视映射和世界上物体的物理尺寸不同而产生了标度变换。在这些领域中，标度不变性是指当图像域的局部尺度发生变化时，图像数据的图像描述或视觉表达效果保持不变<ref name="Lin13PONE" />。在归一化导数响应的尺度上检测局部极大值为从图像数据中获取标度不变性提供了一个通用框架<ref name="Lindeberg1998" /><ref name="Lin14CompVis" />。应用的例子包括'''Blob Detection 斑点检测'''、'''Corner Detection 角点检测、Ridge Detection 脊线检测'''和通过'''Scale-Invariant Feature Transform 标度不变特征变换'''进行的目标识别。

==See also 另见==

==See also 另见==

<small>This page was moved from [[wikipedia:en:Scale invariance]]. Its edit history can be viewed at [[标度对称性/edithistory]]</small></noinclude>

<small>This page was moved from [[wikipedia:en:Scale invariance]]. Its edit history can be viewed at [[标度对称性/edithistory]]</small></noinclude>

[[Category:待整理页面]]

[[Category:待整理页面]]