关键词 > 198:334
198:334 Introduction to Imaging and Multimedia Fall 2023
发布时间:2023-09-28
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
198:334 Introduction to Imaging and Multimedia
Fall 2023 - Course Syllabus
Last updated 9/6/2023 – 10:30am
Instructor: Dr. Ahmed Elgammal -- email: elgammal a-t cs.rutgers.edu
Office hours: Refer to class canvas page for uptodate office hours info
Email policy: please include “CS334” in the subject line. Ignoring this in the subject line might results in email being missed. Student should expect to receive a response within 24 hours on weekday
Regular class time: (All classes will be in person on campus)
Lectures: Mondays and Thursday 12:10- 1:30 PM – PH 115
Recitations: Sec 01 Thu 4:05-5:00 PM SEC-203
Sec 02 Thu 5:55-6:50 PM HLL- 116
There will be no recording of lectures or recitations. Physical attendance is the only option.
Class Web page: Canvas page
TECHNOLOGY REQUIREMENTS: Access to canvas for course materials. Access to computer labs
Course Goals
The aim of CS334 is to introduce fundamental techniques and concepts used in computational imaging and multimedia. Upon completion of this course, a successful student should be able to design and implement programs that deal with image, video, and audio data.
Description:
This is a basic undergraduate-level class that covers the fundamentals of image processing, computer vision and multimedia computing. The students learn about the basics of image, video, and audio formation, representations, and processing, the basics of multimedia compression and representation. The students will be exposed to dealing with image and video data through programming assignments using Java and Python.
Recommended Background:
Linear algebra, basic probability and statistics. Java and Python (you don’t need to know Python in advance, but your will need to pick it up quickly early in the course. We will provide help with that)
Pre-Requisites:
. 01:198:112 OR 14:332:351 (Data Structures)
. 01:198:206 OR 14:332:226 OR 01:640:477 (Discrete Mathematics and Probability)
. 01:640:250 (Linear Algebra)
Topics:
. Introduction to Multimedia: Historical overview, multimedia representations.
. Multimedia Digitization with digital camera as an example. Standard image formats. Colors in images and videos.
. Image Computing: Point Operations, Filters, Binary image analysis: The basics of processing 2D images, thresholding, convolution, edge and corner detection, mathematical morphology, and shape descriptors. Application: implementation of a simple Optical Character Recognition (OCR) System.
. Object detection and recognition in images: intro to deep learning models using convolution neural networks
. Fourier Transform: Understanding frequency components of signals, focusing on imaging.
. Multimedia compression basics: Lossless Compression: Variable length coding, Dictionary based coding. Basics for Lossy Compression: Fourier Transform, Discrete Cosine Transform. Application to image
compression (JPEG compression), Video compression (MPEGs), Audio compression (MP3)
. Multimedia at the age of AI: embedding of text, images, and other media and their applications (text-to-image, text-to-speech, …)
Programming Assignments:
Course assignments will be using Java, and/or Python. We will use ImageJ, which is an image processing library using Java. We will also use imaging libraries in Python.
Textbooks
. W. Burger & M. Burge “Digital Image Processing: An algorithmic introduction using Java”, Springer - Second Edition ISBN 978- 1447166832
Available online through Rutgers Libraries
https://link-springer-com.proxy.libraries.rutgers.edu/book/10.1007%2F978-1-4471-6684-9
. Ze-Nian Li, Mark S. Drew, Jiangchuan Liu “Fundamentals of Multimedia”, Springer 2014, Second Edition ISBN 978-3-319-05289-2
Available online through Rutgers Libraries
https://link-springer-com.proxy.libraries.rutgers.edu/book/10.1007%2F978-3-319-05290-8
. Optional: P. Havaldar and G. Medioni “Multimedia Systems – Algorithms, Standards and Industry Practices”, Cengage Learning – 978- 1-4188-3594- 1 (recommended for some topics – not required)
Course Load
. Homework/programming assignments and small projects: (55%) ~4 assignments. All assignments are
equally weighted
. Quizzes: ~6 quizzes (15%) In class. All quizzes are equally weighted.
. Midterm: in class (15%), in late October – early November
. Final: Online (15%)
. Optional - Extra credit Presentation: 5% can be achieved by researching and presenting a relevant
technology review topic – individuals or groups of 2. Announcement will be made on how to apply.
Tentative Class Calendar (subject to change)
FM: Fundamentals of Multimedia textbook
DIP: Digital Image Processing text book
Week |
Lecture and recitations |
Week 1 |
. Introduction to Multimedia - FM Ch 1 |
Week 2 |
. Multimedia Digitization . Digital Cameras - DIP Ch 2 . ImageJ introduction . Image Formats - DIP Ch 2 or FM Ch 3 |
Week 3 |
. Image Histograms and applications – DIP Ch 4 . Point Operations –DIP Ch 5 |
Week 4 |
. Image Filters & Convolution - DIP Ch 6 |
Week 5 |
. Edges and Corners – DIP Ch 7 & 8 |
Week 6 |
. Convolution Neural Networks. |
Week 7 |
. Object recognition detection, and segmentation |
Week 8 |
. Binary Image Analysis and Morphology – DIP Ch 10 . Region Descriptors – DIP Ch 11 |
Week 9 |
. Color Images, Color spaces: Color spaces for TV and Video; Color spaces for Printing, Colorimetric color spaces. DIP Ch 12 or MS Ch 4 . Color quantization – DIP Ch 12 |
Week 10 |
. Fourier Transform, Discrete Fourier Transform, Discrete Cosine Transform – DIP Ch 13 & 14 |
Week 11 |
. Compression: Intro to Information Theory . Lossless compression: Variable length coding, Dictionary-based coding, LZW compression – FM Ch 7 |
Week 12 |
. Lossy Compression, Image Compression standards, JPEG, JPEG 2000 - FM Ch 8, FM Ch 9 . Video Compression, MPEG1, MPEG2, MPEG4- FM Ch 11 . Audio Compressions: Temporal and Frequency Masking. MP3 – FM Ch 14 |
Week 13 |
. Multimedia in the Age of AI: Text, and Image embeddings and applications to text-to-image, image-to-text etc. |
Week 14 |
. In-class presentations |
Academic Integrity: Rutgers University takes academic dishonesty very seriously. By enrolling in this course, you assume responsibility for familiarizing yourself with the Academic Integrity
Policy and the possible penalties (including suspension and expulsion) for violating the policy. As per the policy, all suspected violations will be reported to the Office of Student Conduct.
Academic dishonesty includes (but is not limited to):
. Cheating
. Plagiarism
. Aiding others in committing a violation or allowing others to use your work
. Failure to cite sources correctly
. Fabrication
. Using another person’s ideas or words without attribution–re-using a previous assignment
. Unauthorized collaboration
. Sabotaging another student’s work in doubt, please consult the instructor