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）︰2020 年 01 月 07 日
考試時限（分鐘）：14:20 ~ 17:20 （原上課時段）
試題：
https://imgur.com/zG1eKtY
https://imgur.com/gBXCCdu
https://imgur.com/9r8igca
1.(28%) 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-O is produced otherwise.
(1)conditioning
(2)labeling
(3)extremum sharpening
(4)Sobel edge detector
(5)facet model
(6)directional derivative
(7)corner detection algorithm
(8)tangent line
(9)fractal
(10)Hough transform
(11)border-tracking algorithm
(12)iterative endpoint fit and split
(13)tangential angle deflection
(14)breakpoint optimization
2.(6%) Please list at least 3 noise removal methods and equations using
neighborhood operators.
3.(6%) Please describe the method, steps, and results of Super Resolution and
Point Spread Function Inverse Filtering for X-Ray Images
4.(6%) Consider the following 3X3 region:
r/c -1 0 1
-1 3 5 9
0 4 7 7
1 0 3 7
The sloped facet is given by α^r + β^c + γ^ . What are the values of
estimated parameters α^, β^, γ^?
Hint:
5.(6%) Please describe the method, steps, and results of Hand Gesture
Recognition with 3D Camera.
6.(6%) Please list three issues of the texture analysis and give a detailed
description for each issue.
7.(6%) Please show the steps of the synthetic texture image generation, that is
, how you can generate new texture images using one original texture image.
8.(6%) Please describe the method, steps, and results of Driver Drowsiness
Detection.
9.(6%) Please list at least three image segmentation methods and explain in
detail
10.(6%) Please calculate the average contrast (C(T)/#E(T)) of all edges.
T=50
[45, 110]
[33,88]
[15, 65]
[45, 115]
[0, 225]
11.(6%) Please describe the method, steps, and results of Filtered Back
Projection for X-Ray Images
12.(6%) Please fit the best straight line L: y=mx+b for the given data points.
(圖片省略，但其三點分別為：(1, 3), (2, 2), (3, 1))
13.(6%) Please describe the method, steps, and results of Medical Image
Segmentation for Pancreas Cancer.
Bonus
14.(2%) Please write the Chinese name of Professor Chiou-Shann Fuh.
15.(2%) What's Professor Chiou-Shann Fuh's pet phrase? (a) 酷斃了Cool (b) 帥呆
人Handsome (c) 好極了Good (d)棒透了Awesome
16.(2%) Is text or joke more important?
17.(2%) Please translate "To err is human, to forgive divine." into Chinese.
18.(2%) Please translate "塞翁失馬，焉知非福" into English.
備註：
(1) 熱騰騰的考題，雖然老師似乎沒有說什麼限制（但是題目卷有收回），可是只有前人
遺愛，才有後人乘涼，故整理了一下po上來
(2) 題目是小精靈生出來的，不要問、很可怕，配分和題目內容我保證有 99.99% 相同。
然後比起期中考改進很多，老師真的有聽進同學的建議(老師好極了)，所以未來修課同學
，千萬要把握可以跟老師說調整方向的機會！！！
(3) 考前有組讀書會+共筆，但因為上課同學都人超好，題目解答都一模一樣也都整理詳細
，所以只要背一背，基本分都能拿到吧；名詞解釋的部分，雖然還是有同學熱血熱心的共
筆，但我完全沒看沒讀，就…希望改題跟期中的時候一樣就好(咳咳
(4) 這次超早交卷，老師雖然還在教室後面，但也沒說什麼/沒留人，考完直接回家休息(
太爽辣)，難得有這種寫不到一小就能走的課(我是說我們那間第一個交的同學XD