為什麼這篇電腦視覺傅楸善github鄉民發文收入到精華區:因為在電腦視覺傅楸善github這個討論話題中,有許多相關的文章在討論,這篇最有參考價值!作者mage594088 (不重要)看板NTU-Exam標題[試題] 108-1 傅楸善 電腦視覺 ...
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)︰2019 年 11 月 5 日
考試時限(分鐘):14:20 ~ 17:20 (原上課時段)
試題:
https://i.imgur.com/a/j2AAsdU.jpg



1.(50%)名詞解釋
(1)shape from texture
(2)shape from shading
(3)alignment
(4)measurement vector
(5)pattern recognition
(6)virtual reality
(7)augmented reality
(8)stereo vision
(9)segmentation
(10)intensity histogram
(11)Gray-Level Co-occurrence Matrix(GLCM)
(12)region
(13)classifier
(14)bounding rectangle
(15)area
(16)centroid
(17)Statistical Pattern Recognition
(18)maximin decision rule
(19)Bayesian decision rule
(20)dilation
(21)opening
(22)recursive neighborhood operator
(23)symbolic domain
(24)linear shift invariant operator
(25)correlation
2.(4%)Please explain in detail classical connected components labeling
algorithm with global equivalence table.
3.(4%) Please explain in detail space-efficient two-pass algorithm that uses a
local equivalence table and run-length encoding.
4.(6%) Please describe the method, steps, and results of Chatbot for Smart
Glasses
5.(6%) Please describe the method, steps, and results of Object Recognition and
Segmentation with 3D Point Cloud with Color Stereo Camera and LiDAR.
6.(4%) Compute the Expected profit for the stiven conditions, notice that P(g)
= 0.95, P(b) = 0.05
Good Bad
Good P(g|g) = 0.8 P(b|g) = 0.2
Bad P(g|b) = 0.2 P(b|b) = 0.9
Good Bad
Good e(g, g) = 2000 e(b, g) = -100
Bad e(g, b) = -10000 e(b, b) = -100
7.(6%) Please describe the method, steps, and results of Circle Measurement
with X-Ray Image.
8.(6%) Please design 3 kernels and steps by using morphological operation to
process Figure A to obtain the result as shown in Figure B.
The size of one pepper and salt noise is 1 pixel. It is necessary to meet the
following conditions:
1. Remove pepper and salt noises.
2. Eliminates small holes.
3. Smooth edge effect. You must write out the operation and kernels that you
use.
For example:
Step 1: opening with a disk of radius 50.
Step 2: dilation with a disk of radius 50...
9.(6%) Please describe the method, steps, and results Watercolorization of
Photographic Image, 10. (4%) Given an input image
10.(4%)Given an input image and a 3x3 kernel (mask), what the output value of
convolution of input pixel (1,1) will be?
A 6.66 B. 7.66 C. 8.77 D. 0.5
(課本Convolution的圖)
11. (4%) What connectivity number of the sequence (A, B, C, D) will be on the
following binary image?
a. (2,3,4,0)
b. (3,4,5,1)
c. (3,4,2,0)
d. (2,0,2,0)
(一樣是課本CH6的圖)
12.(6%) Please describe the method, steps, and results of Vocal Separation for
Music.
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。
然後今年很...的出了50%名詞解釋,真的有夠xx,而且助教說會考的專題部分,通通變
成方法、步驟、結果,同學的愛心都白廢了,整體上考試體驗非常糟,希望未來不會再
這樣了QQ
(3) 考前有組讀書會+共筆,雖然不能說猜題準,但還是有不小幫助,至少有看過的話,
不會完全空白不知道要寫什麼,專題的部分就有啥寫啥,反正改題同學有說,只要有把
關鍵字寫出來,基本都給過~
(4) 考完老師會站在外面賭人,希望給建議跟改進的部分,同學千萬別客氣,有什麼抱怨
盡量說,這樣期末應該會比較好過一些,不過會調分,所以考爛應該也不用太擔心XD
--
※ 發信站: 批踢踢實業坊(ptt.cc), 來自: 110.28.172.114 (臺灣)
※ 文章網址: https://www.ptt.cc/bbs/NTU-Exam/M.1572947541.A.F16.html
答,本來以為只要背好他們給的就行了,結果老師都改成別的了QQ
補一下,結果滿分106,100以上都算100分,平均88,改題有夠鬆,基本上應該是有寫有
分了吧XD,不確定期末成績會怎麼說(雖然還是有人考4x…QQ,是不是沒看我們的共筆啊
※ 編輯: mage594088 (140.112.16.130 臺灣), 11/19/2019 16:21:23