EECS 101 Introduction to Machine Vision (2016-2017)

EECS 101 Introduction to Machine Vision

(Not required for any major. Selected Elective for CSE, CpE and EE.)
Catalog Data:

EECS 101 Introduction to Machine Vision (Credit Units: 3) The use of digital computers for the analysis of visual scenes; image formation and sensing, color, segmentation, shape estimation, motion, stereo, pattern classification, computer architectures, applications. Computer experiments are used to illustrate fundamental principles. Prerequisite: EECS150 or EECS50/CSE50. Electrical Engineering, Computer Engineering, and Computer Science and Engineering majors have first consideration for enrollment. (Design units: 2)

Required Textbook:
. Edition, , 1969, ISBN-13 978-0262081597.

Recommended Textbook:
None
References:
None
Coordinator:
Glenn E. Healey
Relationship to Student Outcomes
No student outcomes specified.
Course Learning Outcomes. Students will:

1. Write programs for analyzing images for various tasks such as noise estimation and segmentation.

2. Write programs to synthesize images using perspective and orthographic camera models.

3. Describe the operation of CCD cameras.

4. Describe the use of derivative masks for gradient estimation and edge detection.

Prerequisites by Topic

Calculus, computer programming.

Lecture Topics:
  • Projection and noise modeling;
  • segmentation, edge detection;
  • Hough Transform;
  • Image synthesis.
Class Schedule:

Meets for 3 hours of lecture and 1 hour of laboratory each week for 10 weeks.

Computer Usage:

Computers are used for weekly programming assignments that illustrate
 fundamental principles of the class in image sensing, segmentation, edge detection, line defection, and image generation.

Laboratory Projects:
  • Projection Modeling 

  • Goals: Student writes programs for orthographic and perspective projection.
  • Design Content: Student designs parameter sets defining the projections.
  • Noise Modeling
  • Goals: Student writes programs for camera noise estimation and modeling.
  • Design Content: Student determines appropriate model and method for displaying fit of model to data Segmentation.
  • Goals: Student writes program for image region segmentation.
  • Design Content: Student designs threshold criteria for region segmentation using histograms Edge Detection.
  • Goals: Student writes program for derivative-based edge detection.
  • Design Content: Student designs orientation quantization and threshold criteria Hough Transform.
  • Goals: Student writes program for line finding using the Hough Transform.
  • Design Content: Student designs two-dimensional quantization space and maximum isolating criteria Image Synthesis.
  • Goals: Student writes programs for generating images of 3-D objects.
  • Design Content: Student designs scene parameters and object property parameters.
Professional Component

Contributes toward the Computer Engineering Topics Courses and Major Design experience.

Design Content Description
Approach:

Machine vision emphasizes implementation and design. Lectures emphasize engineering science and design. Laboratory emphasizes programming and design.

Lectures: 50%
Laboratory Portion: 50%
Grading Criteria:
  • Laboratory/Home work: 30%
  • Midterm exam: 30%
  • Final exam: 40%
  • Total: 100%
Estimated ABET Category Content:

Mathematics and Basic Science: 0.0 credit units

Computing: 3.0 credit units

Engineering Topics: 3.0 credit units

Engineering Science: 1.0 credit units

Engineering Design: 2.0 credit units

Prepared:
July 12, 2016
Senate Approved:
April 29, 2013
Approved Effective:
2013 Fall Qtr