課程名稱︰電腦視覺 (Computer Vision)
課程性質︰資工系(所)選修
課程教師︰傅楸善
開課學院:電機資訊學院
開課系所︰資工系(所)
考試日期(年月日)︰2017 年 11 月 7 日
考試時限(分鐘):14:20 ~ 17:20 (原上課時段)
試題 :
1. (30%) 名詞解釋
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%) 給定一張 6*6 的方格圖,每個格子皆已標上亮度 (0~255)。請解釋什麼是
intensity histogram,並畫出此方格圖的 histogram,觀察 histogram 之後挑一個
適當的 threshold 做 binarize,最後把 binarized image 畫出來。
3. (4%) 解釋什麼是 connected component labeling、signature segmentation。
4. (6%) 方法、步驟、結果:如何從多角度之 X 光圖建構 3D 影像。
5. (4%) 配對投影片第 3 章第 5 頁的四組 intensity histogram - image。
6. (4%) 請用 dilation 與 erosion 定義 opening 和 closing。
7. (10%) 題目給定五組 formula,想問這些公式分別在算什麼。(提示:有 area,
peripheral, centroid, average gray level, gray level variance)
8. (8%) 請將 statistical pattern recognition 的流程畫出來,並且詳細地解釋每個
步驟的細節。(提示:有 unit、measurement vector、decision rule、assignment)
9. (6%) 給定 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),
請推導出 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、步驟、結果:LED 光學滑鼠運作原理
11. (6%) 方法、步驟、結果:圖片霧霾消除之方法
12. (6%) 方法、步驟、結果:手勢(手指頭數量)辨識