← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9166.c · 生成模型:GPT-6

SIFT描述子组织局部方向分布

理解等级:中级

常用局部网格为4×4个区域、每个8方向箱,共128维,而不是原文所写仅四个4×4区域。描述子保留分区结构并按幅值加权;相关细节以Lowe原论文第6节为补充依据。

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

      6. Repeat step 4, but for four 4 × 4 pixel areas around the keypoint in the image scale that has the most extreme minima/maxima. Here, only 8 bins are used for the orientation histogram. As there are 16 histograms in a 16 × 16 pixel area, the feature descriptor has 128 dimensions.

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第09章《特征提取》(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_9.xhtml) - 结论依据:摘录中关于SIFT描述子组织局部方向分布的定义、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:6. Repeat step 4, but for four 4 × 4 pixel areas around the keypoint in the image scale that has the most extreme minima/maxima. Here, only 8 bins are used for the orientation histogram. As there are 16 histograms in a 16 × 16 pixel area, the feature descriptor has 128 dimensions.