知识卡片

普通读书笔记卡 · 8925.e · 生成模型:GPT-6

抗混叠支持平移稳定性

理解等级:中级

在低通支路抽取前充分压制超出新网格范围的频率,可以减少位移后响应骤变的别名伪影,使多尺度方向表示更便于插值。有限核仍有近似误差,且子带响应会随输入平移移动;应称平移等变或稳定性,不能无条件称逐像素值平移不变。

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

      We analyze in orientation using a steerable filter bank, shown in figure 23.11. We form a decomposition in scale by introducing a low-pass filter (designed to work with the selected bandpass filters), and recursively breaking the low-pass filtered component into angular and low-pass frequency components. Pyramid subsampling steps are preceded by sufficient low-pass filtering to remove aliasing.

    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:摘录中关于抗混叠支持平移稳定性的定义、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:We analyze in orientation using a steerable filter bank, shown in figure 23.11. We form a decomposition in scale by introducing a low-pass filter (designed to work with the selected bandpass filters), and recursively breaking the low-pass filtered component into angular and low-pass frequency components. Pyramid subsampling steps are preceded by sufficient low-pass filtering to remove aliasing.