About this course: In this course, you will learn the science behind how digital images and video are made, altered, stored, and used. We will look at the vast world of digital imaging, from how computers and digital cameras form images to how digital special effects are used in Hollywood movies to how the Mars Rover was able to send photographs across millions of miles of space. The course starts by looking at how the human visual system works and then teaches you about the engineering, mathematics, and computer science that makes digital images work. You will learn the basic algorithms used for adjusting images, explore JPEG and MPEG standards for encoding and compressing video images, and go on to learn about image segmentation, noise removal and filtering. Finally, we will end with image processing techniques used in medicine. This course consists of 7 basic modules and 2 bonus (non-graded) modules. There are optional MATLAB exercises; learners will have access to MATLAB Online for the course duration. Each module is independent, so you can follow your interests.
Who is this class for: This class is for anybody that wants to understand the basics of image and video processing; from how are images and videos stored in your phones and transmitted over the Internet to how medical images are used. You will learn regardless of your mathematical and engineering background; students will strong background might be able to get a more in depth understanding. The quizzes are designed not to be too time consuming, our goal is for you to learn and enjoy without stress.
Created by: Duke University
Taught by: Guillermo Sapiro, Professor
Electrical and Computer Engineering
| Commitment | Each module is split in videos, you can finish a module in a week. Quizzes should take minutes. |
| Language | English, Subtitles: Chinese (Simplified) |
| How To Pass | Pass all graded assignments to complete the course. |
| User Ratings |
Syllabus
WEEK 1
Introduction to image and video processing
Learn what is image and video processing. Learn the very basic concepts of human perception needed for understanding image processing. Learn simple tools in signal processing needed to understand following units.
8 videos, 1 reading
- Video: 0 - Welcome and Start Here
- Video: 1 - What is image and video processing (part 1)
- Video: 1 - What is image and video processing (part 2)
- Video: 2 - Course logistics
- Video: 3 - Images are everywhere - Duration 06:31
- Video: 4 - Human visual system - Duration 17:10
- Video: 5 - Image formation - Sampling & Quantization - Duration 28:17
- Video: 6 - Simple image operations - Duration 17:05
- Reading: Optional programming exercises
Graded: Quiz #1
WEEK 2
Image and video compression
JPEG and MPEG are the most successful algorithms in the area, widely used by everybody in a daily basis, and the goal of this unit is to understand how they work. Also to understand why these techniques are important and why they are enabling technologies. Also will describe what is done in the Mars expedition.
7 videos, 1 reading
- Video: 1 - The why and how of compression - Duration 14:16
- Video: 2 - Huffman coding - Duration 20:11 - Optional break at 06:53
- Video: 3 - JPEG's 8x8 blocks - Duration 05:37
- Video: 4 - The Discrete Cosine Transform (DCT) - Duration 25:32 - Optional break at 12:13
- Video: 5 - Quantization - Duration 24:02 - Optional breaks at 08:48 and 17:18
- Video: 6 - JPEG_LS and MPEG - Duration 19:32 - Optional break at 13:45
- Video: 7 - Bonus: Run-length compression - Duration 04:29
- Reading: Optional programming exercises
Graded: Quiz #2
WEEK 3
Spatial processing
Some of the most basic tools in image processing, like median filtering and histogram equalization, are still among the most powerful. We will describe these and provide a modern interpretation of these basic tools. Students will then become familiar with simple and still popular approaches. We will also include non-local means, a more modern technique that still uses classical tools.
14 videos, 1 reading
- Video: 1 - Introduction to image enhancement - Duration 19:11 - Optional break at 08:33
- Video: 2 - Demo - Enhancement & Histogram modification - Duration 03:53
- Video: 3 - Histogram equalization - Duration 19:56 - Optional breaks at 04:40 and 11:30
- Video: 4 - Histogram matching - Duration 08:31
- Video: 5 - Introduction to local neighborhood operations - Duration 06:46
- Video: 6 - Mathematical properties of averaging - Duration 11:00
- Video: 7 - Non-Local means - Duration 07:27
- Video: 8 - IPOL Demo - Non-Local means - Duration 03:38
- Video: 9 - Median filter - Duration 07:20
- Video: 10 - Demo - Median filter - Duration 01:31
- Video: 11 - Derivatives, Laplacian & Unsharp masking - Duration 14:24 - Optional breaks at 05:21 and 11:33
- Video: 12 - Demo - Unsharp masking - Duration 03:10
- Video: 13 - Gradients of scalar and vector images - Duration 05:57
- Video: 14 - Concluding remarks - Duration 01:12
- Reading: Optional programming exercises
Graded: Quiz #3
WEEK 4
Image restoration
The goal of this unit is to complement Unit 3 by adding prior information about the sources of degradation. Students will learn that if we know about the degradation process, we can do better. The objective of this unit is to complete the training with basic and powerful classical tools.
9 videos, 1 reading
- Video: 1 - What is image restoration - Duration 07:49
- Video: 2 - Noise types - Duration 12:43
- Video: 3 - Demo - Types of noise - Duration 03:03
- Video: 4 - Noise and histograms - Duration 04:52
- Video: 5 - Estimating noise - Duration 10:41 - Optional break at 05:03
- Video: 6 - Degradation Function - Duration 11:40
- Video: 7 - Wiener filtering - Duration 12:34 - Optional break at 06:54
- Video: 8 - Demo - Wiener and Box filters - Duration 03:19
- Video: 9 - Concluding remarks - Duration 00:33
- Reading: Optional programming exercises
Graded: Quiz #4
WEEK 5
Image segmentation
Not all parts of the image are the same, and students will learn the basic techniques to partition an image, from simple threshold to more advanced graph cuts and active contours. This is the first unit where student will learn about image analysis and image interpretation, and will learn why this is important, e.g., in medical imaging and object recognition.
12 videos, 1 reading
- Video: 1 - Introduction to Segmentation - Duration 04:17
- Video: 2 - On Edges and Regions - Duration 05:17
- Video: 3 - Hough Transform with Matlab Demo - Duration 20:59
- Video: 4 - Line Segment Detector with Demo - Duration 03:20
- Video: 5 - Otsu's Segmentation with Demo - Duration 14:25
- Video: 6 - Congratulations - Duration 00:17
- Video: 7 - Interactive Image Segmentation - Duration 21:13
- Video: 8 - Graph Cuts and Ms Office - Duration 09:34
- Video: 9 - Mumford-Shah - Duration 05:50
- Video: 10 - Active Contours - Introduction with ipol.im and Photoshop Demos - Duration 05:58
- Video: 11 - Behind the Scenes of Adobe's Roto Brush - Duration 31:29 - Optional breaks at 20:30 and 27:26
- Video: 12 - End of the Week - Duration 00:21
- Reading: Optional programming exercises
Graded: Quiz #5
WEEK 6
Geometric PDEs
This is all optional material. It will help the students that are more mathematically oriented and want to better understand the math behind next unit's lectures. But you will be able to handle without it.The quiz is therefore practice only.This is the first “advanced” unit and smoothly follows from the previous one. Students will learn very modern tools, widely used today, and will contrast with units 3,4 to illustrate how significantly more advanced mathematical tools are also very useful in image and video analysis. We will connect some of these advanced tools with classical ones, e.g., average with heat flow and median with anisotropic diffusion. This will help to provide unified views to the students.
9 videos, 1 reading, 1 practice quiz
- Video: 1 - Introduction to PDEs in Image and Video Processing - Duration 10:22
- Video: 2 - Planar Differential Geometry - Duration 38:33 - Optional breaks at 12:46, 21:03, and 29:41
- Video: 3 - Surface Differential Geometry - Duration 11:43
- Video: 4 - Curve Evolution - Duration 31:10 - Optional breaks at 08:50, 19:25, and 24:22
- Video: 5 - Level Sets and Curve Evolution - Duration 25:34 - Optional break at 14:30
- Video: 6 - Calculus of Variations - Duration 14:03 - Optional break at 06:23
- Video: 7 - Anisotropic Diffusion - Duration 11:17
- Video: 8 - Active Contours - Duration 16:57 - Optional break at 06:23
- Video: 9 - Bonus: Cool Contrast Enhancement via PDEs - Duration 08:32
- Practice Quiz: Quiz #6
- Reading: Optional programming exercises
WEEK 7
Image and video inpainting
Students will get involved with a very exciting topic, since image and video inpainting is one of the most used tools in the movie industry. They will learn the problem, and also how they can approach it from multiple directions. This will also help to illustrate how the same problem can be approached from multiple mathematical angles. We will connect this with Shanon’s work providing yet another angle. If you watched the lectures on PDEs you will have more mathematical background, but you will enjoy this unit and learn without it as well.
7 videos, 1 reading
- Video: 1 - Introduction to Image Inpainting - Duration 08:16
- Video: 2 - Inpainting in Nature - Duration 05:01
- Video: 3 - PDEs and Inpainting - Duration 21:59 - Optional break at 13:31
- Video: 4 - Inpainting via Calculus of Variations - Duration 15:32 - Optional break at 10:06
- Video: 5 - Smart Cut and Paste - Duration 07:51
- Video: 6 - Demo - Photoshop Inpainting Healing Brush - Duration 02:31
- Video: 7 - Video Inpainting and Conclusions - Duration 05:13
- Reading: Optional programming exercises
Graded: Quiz #7
WEEK 8
Sparse modeling and compressed sensing
Here the goal is to present one of the most modern tools in image and video processing, and students will learn something that is today at the top of active research. This will also help to illustrate the use of linear algebra and optimization in image and video processing. This is the last formal unit of the course.
8 videos, 1 reading
- Video: 1 - Introduction to Sparse Modeling - Part 1 - Duration 10:39
- Video: 2 - Introduction to Sparse Modeling - Part 2 - Duration 18:16
- Video: 3 - Sparse Modeling - Implementation - Duration 24:30 - Optional break at 11:58
- Video: 4 - Dictionary Learning - Duration 17:13 - Optional break at 06:03
- Video: 5 - Sparse Modeling Image Processing Examples - Duration 20:57 - Optional break at 09:25
- Video: 6 - A Note on Compressed Sensing - Duration 05:10
- Video: 7 - GMM and Structured Sparsity - Duration 15:40
- Video: 8 - Bonus: Sparse Modeling and Classification - Activity Recognition - Duration 15:10
- Reading: Optional programming exercises
Graded: Quiz #8
WEEK 9
Medical imaging
This is a bonus unit. Enjoy it. Image processing has been very successful in medical imaging, and we will use examples from HIV and brain research to illustrate the importance of image processing in solving societal problems. We will describe the basic tools in these exciting applications, from the acquisition to the analysis.
5 videos
- Video: 1 - Introduction to Medical Imaging - Duration 07:03
- Video: 2 - Image Processing and HIV (Part I) - Duration 23:51 - Optional breaks at 12:37 and 18:39
- Video: 2 - Image Processing and HIV (Part II) - Duration 16:30
- Video: 3 - Brain Imaging, Diffusion Imaging, Deep Brain Stimulation - Duration 26:28
- Video: 4 - Thanks!
FAQs
How It Works
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Creators
Duke University
Duke University has about 13,000 undergraduate and graduate students and a world-class faculty helping to expand the frontiers of knowledge. The university has a strong commitment to applying knowledge in service to society, both near its North Carolina campus and around the world.
Ratings and Reviews
best course ever!!
Good overview of some of the techniques in digital image processing. While a lot of the math was derived, I found in some weeks the explanations were lacking. I used outside sources (other digital image processing courses on youtube and blogs) to get a better understanding of how to implement these algorithms from scratch. Instead of using Matlab's built-in functions, if the professor implemented the algorithms from scratch in Matlab or Numpy, it would have really helped get a clearer picture.
Overall, I enjoyed the course. Thank you.
A+ Awesome class provide a lot of interesting tool for image processing
Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.
© 2018 Coursera Inc. All rights reserved.
SM
Very Nice course. I believe it could be more detailed and elaborated like a 1 or 2 year program so that the students could learn everything at one place. Overall the content was highly motivating and the explanations were very clear.