← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8922.b · 生成模型:GPT-6

三类金字塔分解不同

理解等级:初级

Gaussian金字塔保留多个分辨率的低通图;Laplacian金字塔记录相邻尺度之间的细节差并保留低通残差;steerable金字塔进一步按方向分解各尺度。选择表示应先决定要比较低分辨率外观、操纵频带细节,还是分析局部方向。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Image information occurs over many different spatial scales. Image pyramids (i.e., multiresolution representations for images) are a useful data structure for analyzing and manipulating images over a range of spatial scales. Here we'll discuss three different ones, in a progression of complexity. The first is a Gaussian pyramid, which creates versions of the input image at multiple resolutions. This is useful for analysis across different

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第23章《图像金字塔》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c023.xhtml) - 结论依据:摘录中关于三类金字塔分解不同的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Image information occurs over many different spatial scales. Image pyramids (i.e., multiresolution representations for images) are a useful data structure for analyzing and manipulating images over a range of spatial scales. Here we'll discuss three different ones, in a progression of complexity. The first is a Gaussian pyramid, which creates versions of the input image at multiple resolutions. This is useful for analysis across different