← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9158.a · 生成模型:GPT-6

平滑会同时影响噪声和边界

理解等级:中级

邻域加权平均可减少某些独立高频扰动,使后续梯度响应更稳定,但也会扩散边界并丢失小目标。核尺度越大,平滑范围通常越广;选择应按需要保留的最小结构,而不是追求图像看起来最平滑。

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

      An example of the Gaussian filter in action is shown in figure 8.5. The filter acts as a low-pass filter, suppressing high-frequency components. Indeed, noise in the image is suppressed, leading also to a smoother edge image, which is shown to the right.

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第08章《视觉》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_8.xhtml) - 结论依据:摘录中关于平滑会同时影响噪声和边界的定义、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:An example of the Gaussian filter in action is shown in figure 8.5. The filter acts as a low-pass filter, suppressing high-frequency components. Indeed, noise in the image is suppressed, leading also to a smoother edge image, which is shown to the right.