Course Syllabus

Jump to Today

EEC206 Digital Image Processing

 

Time and Location:

The lecture will be on MW 4:10-5:30P and there is no lab session on Tuesday between 5:30-8:00P. Our synchronous lecture will alternate one week in person @ SOCSCI 80 and one week virtual. All lectures (both in-person and virtual) will be recorded and can be accessed through the zoom menu on Canvas. 

Tentatively, these are the days we will meet in person:  4/3, 4/5, 4/17, 4/19, 5/1, 5/3, 5/22, 5/24, 6/5, 6/7 and Final Project presentation on 6/13 (3:30-5:30P). 

 

We will be using Slack for discussion and information dissemination. The system is highly catered to getting you help fast and efficiently from classmates and instructor. Rather than emailing questions to me, I encourage you to post your questions on Slack under the appropriate folders (homework, programming, lecture, etc.). 

Find our class signup link at: https://join.slack.com/t/image-processinghq/shared_invite/zt-1s1gddozn-yMWHGi2VUfzSHR1kmLjQ7g 

 

Instructor:

Dr. Samson Cheung
Phone: 859-218-0299,  E-Mail: sccheung@ieee.org

Office Hours: M-F 1-2 @https://uky.zoom.us/my/dr.samson.cheung  or

Book appointment at http://drcheung.youcanbook.me/

 

Catalog Description:

Two-dimensional systems theory, image perception, sampling and quantization, transform theory and applications, enhancement, filtering and restoration, image analysis, and image processing systems.

 

Learning Outcomes:

This course introduces digital image processing. It focuses on the theory and algorithms underlying a range of tasks including acquisition and formation, enhancement, segmentation, and representation. By the end of this course, students will be able to

  1. explain how digital images are represented and manipulated, including reading, writing, displaying, extracting pixel and color information as well as performing basic transformations like color space conversion and spatial-frequency transformation. 
  2. write a program that implements fundamental image processing algorithms;
  3. be conversant with the mathematical description of image processing techniques and know how to go from the equations to code, and
  4. to apply techniques learned in the course to solve practical image processing problems.

 

Prerequisites:

  • Basic familiarity with Python
  • Elementary Probabilities and Statistics, eg. EEC161 
  • Signals and Systems, eg. EEC150B

 

Textbooks:

  • Required: Gonzalez and Woods, Digital Image Processing 4th Edition (DIP/4e), Prentice Hall, 2018. [Book website]
  • Optional reference:
    • Szeliski, Richard. Computer Vision: Algorithms and Applications. Springer [Book website, with an electronic version of the book available]
    • Ekman, Magnus. Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers Using TensorFlow. Addison-Wesley Professional, 2021. [Book website, online access through OHE ] 
  • Additional material will be provided by instructors.

 

Topics:

  1. Digital Image Fundamentals
  2. Image Sensing and Representations
  3. Intensity Transformation and Spatial Filtering
  4. Color Image Processing
  5. Transformation Techniques From Fourier to Wavelet 
  6. Image and Video Compression
  7. Basic Image Features and Segmentation
  8. Deep-learning based Image Processing Techniques

 

Course Assignment:

  1. Online homework will be assigned throughout the semester via Canvas.
  2. Team-based (2 students) programming assignments will be assigned through Google Colaboratory platform. Proper documentation of the code, and sample runs and/or graphs must be included to demonstrate the correctness of the implementation
  3. There will be an midterm but no final examination.
  4. There will be a team-based final project (2-3 students) based on the substantial work of a topic selected by the team and approved by the instructor.
  5. The final project has both a final presentation and a report.

 

Online Exam:

Exams in this course will be online. This gives you the flexibility to schedule exams at your convenience and take them wherever you’d like within a 24-hour window

 

Course Grading:

Your grade will be based on:

Weights

Homework

25%

Programming Assignments

25%

Midterm 

20%

Final Project

30%

Total

100%

Grading scale: F: <60, D-: <63, D: <67, D+: <70, C-: <73, C: <77, C+: <80, B-: <83, B: <87, B+: <90, A-: <93, A: <97, A+: otherwise.

 

Course Policy:

  1. All assignments and reports are due on Canvas at 11:59pm on the due dates. 
  2. Late homework with be accepted with 25% of full marks deducted the first 24 hours, 50% the second 24 hours, and not accepted afterwards. 
  3. All course materials are copyrighted and should not be re-posted outside the university.
  4. While students are encouraged to discuss course topics inside and outside of the classroom, individual assignments must be based on individual efforts and team assignments must include discussions on the division of labors. 
  5. Any forms of plagiarism and cheating are strictly prohibited. Violation will result in zero on the assignment and a letter to the department chair. See https://ossja.ucdavis.edu/code-academic-conduct for details.

 

Accommodations for Students with Disabilities:

The university is committed to ensuring equal academic opportunities and inclusion for students with disabilities based on the principles of independent living, accessible universal design, and diversity. I am available to discuss appropriate academic accommodations that may be required for student with disabilities. Requests for academic accommodations are to be made during the first two weeks of the quarter, except for unusual circumstances. Students are encouraged to register with Disability Center (https://sdc.ucdavis.edu/) to verify their eligibility for appropriate accommodations.

Course Summary:

Date Details Due