课程名称︰电脑视觉 (Computer Vision)
课程性质︰资工系(所)选修
课程教师︰傅楸善
开课学院:电机资讯学院
开课系所︰资工系(所)
考试日期(年月日)︰2017 年 11 月 7 日
考试时限(分钟):14:20 ~ 17:20 (原上课时段)
试题 :
1. (30%) 名词解释
Please define the following terms and explain the content, purpose, and
application of each term and give an illustrative example if possible. If
possible, define the term in mathematical equation. For example:
thresholding: an image point operation that produces a binary image from a
gray scale image. A binary-1 is produced on the output image whenever a pixel
value on the input image is above a specified minimum threshold level. A
binary-0 is produced otherwise. Alternatively, thresholding can produce a
binary-1 on the output image whenever a pixel value on the input image is
below a specified maximum threshold level. A binary-0 is produced otherwise.
(1) grouping
(2) labeling
(3) shape
(4) feature
(5) preserve order
(6) hexagonal grid
(7) corner
(8) edge
(9) linear shift-invariant operator
(10) mathematical morphology
(11) conditioning
(12) convolution
(13) cross correlation
(14) weight mask
(15) noise cleaning
2. (10%) 给定一张 6*6 的方格图,每个格子皆已标上亮度 (0~255)。请解释什么是
intensity histogram,并画出此方格图的 histogram,观察 histogram 之后挑一个
适当的 threshold 做 binarize,最后把 binarized image 画出来。
3. (4%) 解释什么是 connected component labeling、signature segmentation。
4. (6%) 方法、步骤、结果:如何从多角度之 X 光图建构 3D 影像。
5. (4%) 配对投影片第 3 章第 5 页的四组 intensity histogram - image。
6. (4%) 请用 dilation 与 erosion 定义 opening 和 closing。
7. (10%) 题目给定五组 formula,想问这些公式分别在算什么。(提示:有 area,
peripheral, centroid, average gray level, gray level variance)
8. (8%) 请将 statistical pattern recognition 的流程画出来,并且详细地解释每个
步骤的细节。(提示:有 unit、measurement vector、decision rule、assignment)
9. (6%) 给定 E = P(g,g)e(g,g) + P(g,b)e(g,b) + P(b,g)e(b,g) + P(b,b)e(b,b),
请推导出 E = { [1-P(b|g)]e(g,g) + P(b|g)e(g,b) } P(g) + { P(g|b)e(b,g) +
[1-P(g|b)]e(b,b) } [1-P(g)]
10. (6%) 方法、步骤、结果:LED 光学鼠标运作原理
11. (6%) 方法、步骤、结果:图片雾霾消除之方法
12. (6%) 方法、步骤、结果:手势(手指头数量)辨识