eng 7854 / 9804 industrial machine vision course syllabus – winter ...

geckokittenΤεχνίτη Νοημοσύνη και Ρομποτική

17 Οκτ 2013 (πριν από 3 χρόνια και 9 μήνες)

135 εμφανίσεις

ENG 7854/9804 – Industrial Machine Vision page 1 of 4

ENG 7854 / 9804
INDUSTRIAL MACHINE VISION

COURSE SYLLABUS – WINTER 2010


Instructor:
Professor Nicholas Krouglicof
Office:
EN-3051
Phone:
(709) 737-3745
E-mail:
nickk@mun.ca

Webpage:
http://www.engr.mun.ca/~nick/eng8805



Class Schedule:

Lecture Mon. / Wed. / Fri. 12:00 to 12:50 pm EN1052
Office Hours Wed. / Fri. 2:00 to 4:00 pm EN3051

Course Description:

ENG 7854/9804 Industrial Machine Vision is a combined senior undergraduate /
graduate course in computer vision with an emphasis on techniques for automated
inspection, object recognition, mechanical metrology, and robotics. Image processing
courses typically focus for image enhancement, restoration, filtering, smoothing, etc.
These topics will be covered to a certain degree but the main focus will be on image
segmentation, feature extraction, morphological operators, recognition and
photogrammetry. Issues related to the efficient software implementation of these
techniques for real-time applications will also be addressed.



Topics Covered:

WEEK TOPIC
0
Jan. 8

Introduction
• Course outline
• Presentation of course projects

1
Jan. 11
Jan. 13
Jan. 15
Software Primer
• Matlab Image Processing Toolbox
• Building GUIs with Matlab
ENG 7854/9804 – Industrial Machine Vision page 2 of 4


2
Jan. 18
Jan. 20
Jan. 22
Image Formation Process
• Elements of a machine vision system
• Image model: perspective geometry, image function
• Radiometrical model: energy flux, radiant intensity, irradiance, photon
noise
3
Jan. 18
Jan. 20
Jan. 22
Mathematical Preliminaries
• Two-dimensional Fourier transform
• Convolution theorem
• Sampling theorem
• Nonlinear least-squared-error fitting
4
Jan. 25
Jan. 27
Jan. 29
Image Enhancement
• Gray Scale Modification
• Histogram Modification
• Image restoration: Laplacian operator
• Image filtering operations: sharpening, smoothing, averaging, median
filtering
5
Feb. 1
Feb. 3
Feb. 5
Low Level Segmentation
• Gray level thresholding
• Locally adaptive thresholding
• Edge detection
6
Feb. 8
Feb. 10
Feb. 12
High level Segmentation
• Tesselation and connectivity
• Connected component labeling
• Crack and border following
7
Feb. 15
Feb. 17
Feb. 19
Representation Schemes
• Rows: runs, binary trees
• Blocks: medial axis transformation, quadtrees
• Borders
8
Feb. 26
“Blob” Analysis
• Form parameters that are independent position, orientation, scale
• Complexity, circularity
9
March 1
March 3
March 5
“Blob” Analysis (continued)
• Midterm Exam on March 1
• Moment invariants
• Principal axis
10
March 8
March 10
March 12
Morphological Image Processing
• Binary erosion/dilation, opening/closing, hit-or-miss transforms
• Gray-scale morphology
11
March 15
March 17
March 19
Recognition
• Hough transform techniques
• Geometric constraints
• Matching
• Classification
ENG 7854/9804 – Industrial Machine Vision page 3 of 4


12
March 22
March 24
March 26
Photogrammetry and Camera Calibration
• Mathematical preliminaries
• Sub-pixel interpolation
• Camera Calibration: Intrinsic and extrinsic parameters
13
March 29
March 31
TBA
14
April 5
April 7
Presentation and Demonstration of Term Projects



References:

1. Ballard, D.H. and Brown, C.M., Computer Vision, Prentice-Hall Inc., Englewood
Cliffs, New Jersey, 1982.

2. Davies, E.R., Machine Vision: Theory, Algorithms, Practicalities, Academic Press,
London, 1990.

3. Dougherty, E.R., An Introduction to Morphological Image Processing, SPIE Optical
Engineering Press, Bellingham, Washington, 1992.

4. Grimson, W.E.L., Object Recognition by Computer: The Role of Geometric
Constraints, The MIT Press, Cambridge, Massachusetts, 1990.

5. Haralick, R.M. and Shapiro, L.G., Computer and Robot Vision (Volumes I and II),
Addison-Wesley, Reading Massachusetts, 1990.

6. Rosenfeld, A. and Kak, A.C., Digital Picture Processing (Volumes I and II), 2
nd

Edition, Academic Press, Orlando, Florida, 1982.

7. Selected journal publications


Evaluation:


The final grade for the course will be determined as follows:

1 Assignments 15
2 Oral Presentation & Project 35
3 Midterm 15
4 Final Exam 35
Total: 100
ENG 7854/9804 – Industrial Machine Vision page 4 of 4


Exams:

• All exams are closed-book.
• The midterm exam is tentatively scheduled for Monday, March 1, 2010.


Assignments:


Two major assignments will be assigned immediately after the presentation of the
relevant material in class. These assignments will normally involve the software
implementation of techniques presented in class.


Additional minor exercises may be assigned as required.


Term Project:

• A major part of this course is the term project which is worth 35% of the final grade.
• Projects will be undertaken by teams of no more than two undergraduate students.
• Projects for graduate students will be undertaken on an individual basis.
• Teams can define their own projects subject to the following conditions:

1. Teams must have an operational machine vision system that can be
demonstrated to the class by the end of the semester.
2. Undergraduate students should target a realistic application of machine vision
related to industrial inspection, grading, tracking, object recognition,
metrology, robotics, etc.
3. Graduate students should base their project on the implementation of
techniques or algorithms presented in one or more journal publications.

• Project proposal are due on Friday, January 15, 2010 and must include the
following:

1. A problem statement.
2. A description of the proposed machine vision system. What useful purpose or
function will your system serve?
3. A description of the software tools and hardware (if applicable) that will be
used.
4. The deliverables - what will your team demonstrate to the class at the end of
the term.
5. A brief state-of-the-art survey of comparable systems.
6. Pertinent references.