week01-holeCounting.ppt
Download
Report
Transcript week01-holeCounting.ppt
Computer Vision: Week 1 Intro.
What are its goals?
What are the applications
What are some ways of using images
(Later: methods and programming)
Stockman MSU/CSE Fall 2009
1
First day course business
Syllabus on web
Homework 1 specs on web (due 12 Sep)
Course web pages
(www.cse.msu.edu/~cse803)
Computer accounts: DECS or CSE
Textbook by Shapiro and Stockman
Read both Chapters 1 and 2
Read outside reading S1 (.pdf online)
Stockman MSU/CSE Fall 2009
2
Manufacturing case
100 % inspection needed
Quality demanded by major buyer
Assembly line updated for visual inspection
well before today’s powerful computers
Stockman MSU/CSE Fall 2009
3
Simple Hole Counting Alg.
Customer needs
100% inspection
About 100 holes
Big problem if any
hole missing
Implementation in
the 70’s
Alg also good for
counting objects
Stockman MSU/CSE Fall 2009
4
Imaging added to line
Camera placed
above conveyor
line
Back lighting
added
1D of image from
motion of object
past the camera
Stockman MSU/CSE Fall 2009
5
Critical “corner patterns”
“external corner”
has 3(1)s and
1(0)
“internal corner”
has 3(0)s and
1(1)
Holes computed
from only these
patterns!
Stockman MSU/CSE Fall 2009
6
Hole (Object) Counting Alg.
Stockman MSU/CSE Fall 2009
7
#holes = (#e - #i)/4
Stockman MSU/CSE Fall 2009
8
Variations on Algorithm
Easy if entire image is in memory
Only need to have 2 rows in memory at any
time
* used in the 1970’s
* can allow special hardware
Relate to driving around city blocks.
Check out C++ program and results on web.
Stockman MSU/CSE Fall 2009
9
Industrial vision/inspection
Literally thousands of applications
Usually very specific engineering
Usually called “image processing” – not
“computer vision”
See Oshawa-Stemmer video
See John Deer application
Stockman MSU/CSE Fall 2009
10