Multidimensional Digital Signal Processing

ECG782 Spring 2023

Description

Professor:
Dr. Brendan Morris,
SEB 3216
OH: TBD. Most likely will only be by appointment.

Lecture: W 09:00-10:00, Virtual
Final: W May 10, Online
Look up your final exam schedule now to determine conflicts.

Textbook

Digital Image Processing, 3rd Edition, Gonzalez and Woods, ISBN: 978031687288.
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools and Techniques to Build Intelligent Systems, 2nd Edition, Geron, ISBN: 9781492032649.

Recommended Text

Image Processing, Analysis, and Machine Vision, 4th Edition, Sonka, Hlavac, and Boyle, ISBN: 978-1-133-59360-7 Available online [link]
Computer Vision: Algorithms and Applications, Richard Szeliski. Available online [link]

Catalog Description:

Theory and applications of multidimensional (M-D) digital signal processing. M-D signals and systems. M-D z-transform. M-D DFT and FFT. Design and implementation of M-D FIR and IIR filters. Applications to image processing such as image enhancement and restoration. Advanced topics chosen according to class interests.
Prerequisites: ECG782

Course Syllabus: [pdf]

Grading

ComponentPercentageDate
Midterm: 20% TBD
Final: 20% 05/10
Project: 25% 05/03
Homework: 15% Weekly
Presentation: 10% -
Participation: 10%

Students may work together in study groups but all assignments must be completed individually. Homework will be due in class on the designated date. No late homework will be accepted unless prior notification and arrangements are made. The course will have a final computer vision term project. You will be required to submit a project report in the form of a conference styled manuscript and make a presentation.

Gradebook

The gradebook is available through UNLV Webcampus [link].

Announcements

DateNote
01/25/23 Welcome to Spring 2023. This class utilize Matlab/Python/OpenCV/TensorFlow/PyTorch for programming and Latex for assignments.

Schedule (Tentative)

WeekDateLecture TopicReadingAssignment
1 01/16 M class01: Course Info [pdf] Intro [pdf] GW Ch 1 [pdf], 2 [pdf] HW00 [pdf]
Due --
01/18 W class02: Image Fundamentals [pdf]
2 01/23 M class03: Spatial Filtering [pdf] GW Ch 3 [pdf] HW01 [pdf]
Due Su 1/29
Solutions [pdf]
01/25 W class04: Spatial Filtering
3 01/30 M class05: Color IP [pdf] Morphology [pdf] GW Ch 6 [pdf], 9 [pdf] HW02 [pdf]
Due Su 2/05
Solutions [pdf]
02/01 We class06: Frequency Domain Filtering [pdf][WebEx]
4 02/06 M class07: Frequency Domain Filtering [pdf] GW Ch 4 [pdf] HW03 [pdf]
Due Su 2/19
Solutions [pdf]
02/08 W class08: Segmentation [pdf] [WebEx]
5 02/13 M class09: Segmentation GW Ch 10 [pdf]
02/15 W class10: Motion [pdf] [WebEx]
6 02/20 M class11: Presidents Day Holiday Szeliski Ch 8
Sonka Ch 16 [pdf]		 HW04 [pdf]
Due Su 3/05
Solutions [pdf]
02/22 W class12: Motion [WebEx]
7 02/27 M class13: Keypoints [pdf] Szeliski Ch 4 [pdf]
[Stauffer and Grimson 1999] [pdf]
03/01 W class14: Mixture of Gaussian Background Model [pdf] [WebEx]
8 03/06 M class15: Project Introduction [pdf]
Reading List [link]		 Project Description [pdf]
Project Examples [pdf]
Reading List [link]		 HW05 [pdf]
Due Su 3/26
03/08 W class16: Project [Webex]
9 03/13 M Spring Break
03/15 W Spring Break
10 03/20 M class17: Midterm
03/22 W class18: Midterm [WebEx]
11 03/27 M class19: Object Recognition [pdf] Sonka Ch 9 [pdf]
Szeliski 2e Ch 6
[Viola Jones 2001] [pdf]
03/29 W class20: Viola-Jones Detector [pdf][WebEx]
12 04/03 M class21: Machine Learning (ML) Overview [pdf] Geron Ch 1 [pdf]
Geron Ch 10 [pdf]
04/05 W class22: Artificial Neural Network (ANN) Overview [pdf][WebEx]
13 04/10 M class23: Deep Computer Vision Using CNNs [pdf] Geron Ch 14 [pdf]
04/12 W class24: CNNs [WebEx]
14 04/17 M class25: Object Detection Deep Recognition [pdf] HW06 [pdf]
Due Su 5/07
04/19 W class26: Segmentation
15 04/24 M class27:
04/26 W class28:
16 05/01 M class29: Project Presentations
05/03 W class30: Project Presentations
17 05/08 M Review
-
05/10 W Final