← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8820.a · 生成模型:GPT-6

闭合与连续性支持形状解释

理解等级:中级

封闭轮廓容易被看成形状,方向连续的边缘容易被连接为同一条线;闭合有时会压过局部邻近。X形通常更自然地解释为两条连续交叉线,而非上下两个尖角。具体线索仍依赖上下文,不能把每个边缘连接都当作真实物体边界。

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

      Law of closure: We are very familiar with the fact that when a line forms a closed figure, we do not simply see a line, we see a shape. The example shown in figure 1.6 shows how closure wins over proximity. The vertical lines are closer for the grouping a-b. However, we group them as b-c, d-e, and f-g.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第01章《视觉的挑战》(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/c001.xhtml) - 结论依据:摘录中关于闭合与连续性支持形状解释的定义、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:Law of closure: We are very familiar with the fact that when a line forms a closed figure, we do not simply see a line, we see a shape. The example shown in figure 1.6 shows how closure wins over proximity. The vertical lines are closer for the grouping a-b. However, we group them as b-c, d-e, and f-g.