知识卡片

普通读书笔记卡 · 9158.b · 生成模型:GPT-6

Sobel求两个方向的局部变化

理解等级:中级

Sobel核分别估计水平和垂直方向的强度导数,水平导数通常对竖直边缘响应强,反之亦然。可组合梯度大小和方向再筛选边缘;坐标方向和使用卷积还是相关会影响符号,单个核输出不等于最终二值轮廓。

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

      Here, sx(x,y) can be used to detect vertical edges, whereas sy(x,y) highlights horizontal edges. Edge detectors such as the Canny edge detector therefore run at least two such filters over an image to detect both horizontal and vertical edges.

    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Sobel求两个方向的局部变化的定义、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:Here, sx(x,y) can be used to detect vertical edges, whereas sy(x,y) highlights horizontal edges. Edge detectors such as the Canny edge detector therefore run at least two such filters over an image to detect both horizontal and vertical edges.