Course Objective: An introduction to the fundamentals and the theory of multidimensional signal processing, digital image processing, machine learning for visual data, key applications in multimedia products and services

Course Primary Instructor: Prof. Ghassan AlRegib (alregib@gatech.edu)

Course Days/Times: MW 11:00 a.m. -12:15 p.m.

Class Location: KLAUS 2443

We will meet in person in class for lectures. In some weeks, there will be videos that I would like you to watch before class. Depending on the lengths of such videos, watching them may constitute a lecture. In such a case, we will not meet during lecture hour. You will be informed at the beginning of the week to plan your lectures attendance and/or video watching. Therefore, it is crucial to check the schedule on Canvas, on a daily basis.  Students are expected to be familiar with and abide by the Institute guidelines, information, and updates. Find campus operational updates and Frequently Asked Questions on the Tech Moving Forward site.    

Mondays and Wednesdays, 01:00-02:00 p.m. on zoom at this link: https://gatech.zoom.us/j/96683846989 

Course TAs:

TBA

Communications: Avoid emails. You can use PIAZZA to send a message to me or to me & the TA(s).

Announcements: Official announcements will be posted on Canvas, via Piazza, or announced during lectures.

Textbook:  No required textbook

References:

1. R.C. Gonzalez and R.E. Woods, Digital Image Processing, 3rd edition, Prentice-Hall, 2008
2. M. Petrou and C. Petrou, Image Processing: The Fundamentals, 2nd Edition, Wiley, 2010
3. J. W. Woods, Multidimensional Signal, Image, and Video Processing and Coding, 2nd Edition, Academic Press, 2012
4. A.K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall, 1989
5. J.S. Lim, Two-dimensional Signal and Image Processing, Prentice-Hall, 1990
6. M.J.T. Smith, A. Docef, A Study Guide for Digital Image Processing, Scientific Pub., 1999

Prerequisite: For graduate students: a course in digital signal processing (e.g., ECE4270 or equivalent). For undergraduate students: ECE 2026 [min C] (or equivalent) and Prerequisites with concurrency: ECE 3077 [min C] or ISYE/MATH/CEE 3770 [min C] or MATH 3670 [min C]

I expect students to be familiar with programming.

 

Canvas: Go to  https://canvas.gatech.edu/ and if you do not see the class page, make sure you are registered for the course.

Piazza: Students are expected to utilize PIAZZA platform to post questions and engage into online discussions. Make sure you enroll into the course site on Piazza via this URL: https://piazza.com/gatech/fall2023/ece6258ece4803bmed8813. If you have any difficulty, you can email team@piazza.com.

Academic Honesty: All violations of the Georgia Tech Honor Code will be handled by referring the case directly to the Dean of Students for investigation and penalties. The complete honor code can be found in the GT Policy Library: http://www.policylibrary.gatech.edu/student-affairs/academic-honor-code

Campus Support: Reach out to the Dean of Students Office, the CARE Center, the Counseling Center, Stamps Health Services, and the Student Center. Student Center services and operations are available on the Student Center website. For more information on these and other services, visit the Division of Student Life.    

Office of Disability Services: If you are a student registered with the Office of Disability Services (ODS), please make sure the appropriate forms and paperwork are completed with the instructor within the first week of classes. The instructor will abide by all accommodations required by ODS. The schedule for exams is posted in the syllabus and any potential modifications or changes will be made with at least one week’s notice. It is the responsibility of the student to properly arrange test accommodations for each exam with ODS in sufficient time to guarantee space for exam administration. ALL exam accommodations must be handled through ODS. If the student does not register accommodations with ODS for the taking of an exam, then they will have to take the exam at the normally scheduled times without any additional accommodation unless the instructor is given specific directive from ODS on the student’s behalf due to a mitigating circumstance.

Grading:

For Undergraduate students:

Homework (- lowest)	Exams 1+2+final	Project*
40%	15+15+30=50%	10%

For Graduate students:

Homework (- lowest)	Exams1+2	Project
40%	15+15=30%	30%

* The project for undergraduate students will be optional and graded for a bonus credit of 10%.

Exams Dates (subject to change):

        Exam #1:    Wed., September 27, 2023

        Exam #2:    Wed., October 25, 2023

        Final Exam for UG: Scheduled on Fri., Dec. 08, 2023  11:20 a.m. – 02:10 p.m.

Remarks:

• No Homework assignments will be accepted nor graded after the posted due date/time
• No Make-up exams. If you have to be absent for an exam, you need to inform me in advance with an official justification, i.e., official paperwork.

Due Dates: Assignments are due on Fridays @5pm, unless stated otherwise, for all sections except Section Q. Section Q will have a 3-day delay, until the following Monday @5pm.

Assignments Submission:  All homework assignments need to be submitted online. Read the instructions of each assignment carefully. Most assignments will be a mix of theoretical questions and programming exercises—the former to test the students’ grasp of lecture concepts and the latter to evaluate their proficiency in applying those concepts to use cases.

Programming Language: The homework assignments have hands-on exercises that involve programming. I encourage the utilization of Python. We have prepared a library called dippykit to help you perform such assignments, https://dippykit.github.io/dippykit/. Prior familiarity with Python is preferred but not necessary. Students who are familiar with Matlab® but would like to use this opportunity to learn Python may find this tutorial helpful.  Instructions to set up your PC to run python scripts can be found on the dippykit page. Alternative setup, using Anaconda, can be found on this page. In any case, students are free to use other languages/packages such as C/C++ and Matlab®.

 

Term Project:

Teams: Students in graduate sections must work on the term project in teams of TWO students; no exception. If we end up with an odd number of students, we may allow one team to have three students. You may utilize Piazza to team up.

Topics: The project will be to denoise and enhance images from the CURE-OR, CURE-TSR, CURE-TSD, SSID, BSD-68, and Set-12 datasets. Every team must select one noise type from each of the datasets. A noise type cannot be picked by more than 4 teams; the exact number will be finalized after the registration phase is concluded. A system to pick the noise types will be released and announced ahead of time. A team cannot pick similar noise types across the three datasets.  Evaluation of the performance should be based on IQA metrics and detection/recognition accuracy metrics.

Progress Report (15% of the project’s grade): On October 20, 2023, teams are expected to submit a one-page progress report that details the completed tasks, details of the individual’s work, and their overall plan.

Poster Presentation (35%): Teams are expected to present their final term project during the final three lectures. Every team will have a 10-minute poster presentation including Q&A. 

Term Paper (50%): The term paper is due on December 01, 2023 at 05:00 p.m. The term paper must follow an IEEE Double-column, single-space, 11-pt font size format. Use a Letter size template. A template can be found HERE. 

Project Grade Distribution:

Progress Report: 15%  

Poster Presentation: 35% 

Term Paper: 50%

*Undergraduate students who choose to do the project for a bonus of up to 10% will be evaluated based on a poster AND a term paper. Undergraduate students can work on in groups of sizes 1 to 2 members. Such intentions and teams must be declared by the progress report deadline of October 20, 2023.