CPE 631 (2009) / CPE 488

gurgleplayΤεχνίτη Νοημοσύνη και Ρομποτική

18 Οκτ 2013 (πριν από 4 χρόνια και 23 μέρες)

122 εμφανίσεις


CPE 631 (200
9
)

/ CPE 488

Machine Vision


Computer Engineering
Department

King Mongkut's University of Technology, Thonburi

Course Information

Instructor
:

Suthep Madarasmi, Ph
.
D
. (
suthep@kmutt
.
ac
.
th
)

Website
:

ww
w.cpe.kmutt.ac.th/~suthep/cpe631

Time
:


Friday
17:
00
-
19:0
0
,
CB 40805

Offic
e Hours:

Friday 16:
00


17:0
0

TA.:


Ms. Varin Chouvatut
(
varin@cpe.kmutt.ac.th
)

Office Hours:

Thursdays 13:30


1
4
:
3
0 at Sigma L
ab.

Course Overview

To introduce students to the concepts of
machine

vision touching on areas of
computer graphics, image processing, artificial intelligence, biological vision,
neural networks, pattern recognition and robot vision
.
The course will be
pr
oject
-
oriented consisting

of a lecture to introduce the subject matter followed
by
discussions on computer vision application
s and assignments to learn the
subject matter
.
Computer vision can be viewed as the inverse problem of
computer graphics
:
the ob
jective of computer graphics is to generate images
using a model of the world whereas the objective of computer vision is to arrive
at a description of the world using images
.
Image processing will be covered
extensively with topics such as edge finding, i
mage enhancement, image
segmentation, and clustering
.
Linear, non
-
linear, and stochastic

optimization
methods will be introduced for use in solving computer vision problems
.
The
inverse optics problem in computer vision will be discussed including stereo
v
ision, shape from shading, and other Shape from X algorithms
.
Finally, we will
discuss several algorithms for image understanding such as scene interpretation,
object recognition, and face recognition
.


Assignments

1.

Simple Thai OCR Competition
:
Correlation,

edge detection, thinning, image
segmentation,
and
template matching
.
Undergraduates can form groups of 2
persons for the assignment. Graduates must do individually.
(1
5
%)

2.

T
erm project will be on a computer vision topic of choice requiring
:



Proposal
: 1
-
2

pages and
5

min
utes presentation.



Project
:
20

min
utes

presentation

for project work, 30 minutes for
literature review lecture.


Text

Jain R
.
, R
.
Kasturi, and B
.
G
.
Schunck, Machine Vision, McGraw
-
Hill
.


Course Topics

1
.

Overview of Computer Vision


Course and Assignments Overview

Image Formation and Sensing

3
-
D Computer Graphics and Visual Realism

Digital Images
:
bw, grayscale, and color

2
.

Binary Image Processing
:
Low
-
level

Image Filtering and Edge Detection

3
.

Regions, Image Segmentation, Textu
re Segmentation

Blob Coloring

4
.

Contours and Boundary Detection

General Hough Technique and Applications



5
.

3
-
D Computer Graphics Models Revisited



Optics, Curves and Surface

6
.

Optimization: Pseudo
-
Inverse, Hough Technique.

7.

Optimizati
on: Energy Minimization

Gradient Descent, Image Cleanup


Back Propagation Neural Networks

Computing Optical Flow

8
.

Optimization: Bayesian Probability, Pixel Lattice

Gibbs Sampler and Simulated Annealing


Depth from Stereo Vision

9
.

Optimizat
ion: Genetic Algorithms


Optimal Material Consumption

10
.

Depth & Shape from X,
Texture, Contour, Stereo

11
.

Calibrations
, Structure from Motion, Object Tracking

12
.

Shape from Shading

13
.

Camera Pose Estimation and Augmented Reality

14
.

Object Recog
nition Models


Grading

Programming Assignment 1


15
%


Assignment 2 (Term Project)


20
%

Best 9 of
1
1

Quiz



65
%