EECS225B, Spring 2020
Digital Image Processing
Mondays and Wednesdays, 12:30-2:00pm
540 Cory
Required Text:
-
R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice Hall, 4th Edition.
Video lectures:
EE225B, Spring 2006
Course Details:
|
Lecturer:
Professor Avideh Zakhor
avz@eecs.berkeley.edu
507 Cory Hall
Phone: (510) 643-6777
Office Hours:
Wed. 2:00pm - 3:00pm in 507 Cory
TA:
Scott McCrae
mccrae@berkeley.edu
|
|
Recommended Books:
- Bovik, Handbook of Image and Video Processing, Academic Press 2000.
- N. Netravali and Barry G. Haskell, Digital Pictures, Plenum Press, 1988.
- W.K.Pratt, Digital Image Processing, John Wiley and Sons, 1992.
- A.M. Tekalp, Digital Video Processing, Prentice Hall, 1995.
- Szeliski, Richard. Computer vision: algorithms and applications. Springer Science & Business Media, 2010. PDF
- Ponce, Jean, et al. Computer vision: a modern approach. Computer 16.11 (2011). PDF
Other useful resources online: Coursera course
- Fundamentals of Digital Image and Video Processing
- Deep Learning in Computer Vision
- Image and Video Processing: From Mars to Hollywood with a Stop at the Hospital
Outline of Topics:
-
-
Introduction
- Applications
-
Elements of visual perception, Structure of the human eye, Image Formation in the Eye, Brightness Adaptation and Discrimination
-
-
Light and Electromagnetic Spectrum
-
Image sensing and acquisition
-
Sampling and quantization
-
-
Spatial transformations; intensity transformations and spatial filtering; Linear filters; order statistics nonlinear filters
- Frequency domain filtering, sharpening filters; homomorphic filtering
-
Image enhancement; histogram processing, equalization, matching
-
-
Basics of deep learning; variations of neural networks; CNNs and GANS
-
Applications to classification, object detection, semantic segmentation
-
-
Image restoration; noise models; order statistics filters; adaptive filters
-
Estimation of degradation function; Weiner filtering; inverse filtering; constrained least squares filtering
-
Restoration using deep neural networks
-
-
X-ray tomography, projections, radon transform
-
Reconstruction from projections; Fourier slice theorem; back-projections
-
Tomography using deep neural networks
-
-
Continuous and discrete wavelet transform and relationship to subband coding
-
-
Image compression basics
-
What to code, space domain coding; transform coding, DCT, wavelet transform
-
Linear and nonlinear quantization
-
Bit allocation: entropy; Huffman coding; arithmetic coding
-
JPEG 2000 basics; spatial scalability; bit rate scalability
-
Motion estimation, video coding basics, video standards
-
Applications of deep learning to compression
-
-
Edge detection
- Segmentation using graph cuts
- Keypoint detectors
- Feature extraction; SIFT, MSER
- Feature matching and RANSAC
-
- Morphological filtering; dilation, erosion; closing, opening
-
- Super resolution: classical methods and deep neural networks
Homework:
Homework will be issued approximately once a week. They will either consist of written assignments, Matlab assignments or C programming assignments. Homework will be graded, and will contribute 60% to the final grade, where 20% is for reading assignments and 40 percent is for actual homework. Homework handed in late will not be accepted unless consent is obtained from the Professor prior to the due date.
There will be a project that will constitute 35% of your grade. The project can be individual or in a group. You are to submit a proposal to the instructor by the end of March. More details on the project will be provided later, and a list of suggested topics will be provided. In addition, 5% of your grade will be for in class participation. The participation will be determined by 15 minute presentation of teams of 2 students on review of two or three research papers assigned by the instructor.
|
-
Welcome to EE225B!
-
Please sign up for the class piazza page at this link: piazza.com/berkeley/spring2020/eecs225b
- Lecture 1: Introduction.
Wed. Jan. 22, 2020.
- Lecture 2: Introduction pt 2.
Mon. Jan. 27, 2020.
- Lecture 3: Sampling and Quantization.
Wed., Jan. 29, 2020.
- Lectures 4 and 5: Neural Networks.
Mon. Feb. 3 and Wed. Feb. 5, 2020.
- Lecture 6: Histogram Matching (1).
Mon. Feb. 10, 2020.
-
Lecture 7: Histogram Matching (2).
Wed. Feb 12, 2020.
-
Lectures 8, 9, 10: Filtering in the Frequency Domain.
Feb 19, 24, 26, 2020.
-
Lectures 11, 12: Image Restoration and Reconstruction. ( Additional reading on restoration.)
March 2, 4, 2020.
-
Lecture 13: Weiner Filter derivation, additional lecture material on random processes.
March 9, 2020.
-
Lecture 13: Image Reconstruction from Projection.
March 11, 2020.
-
Lectures 14 and 15, slides for:Waveform coding, Objectives of image coding, and Methods of bit assignment.
March 16 and 18, 2020.
-
Lectures 16 thru 20, March 30 thru April 13
-
Lectures 21 and 22, April 13 and 15
-
Lecture 23: Zero tree coding
April 20, 2020.
-
Additional lecture material: Ill-conditioned algorithm problem; Reconstruction from partial Fourier Transform; Reconstruction from partial Fourier Transform, handwritten; Reconstruction from Level Crossing.
- Paper Review #1. Due February 3rd at 9am.
- Ledig et al., "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network", CVPR 2017.
- Yang et al., "Deep Learning for Single Image Super-Resolution: A Brief Review", IEEE Transactions on Multimedia, Vol 21 No 21, 2019.
- Yang et al., "Image Super-Resolution Via Sparse Representation", IEEE Transactions on Image Processing, Vol 19 No 11, 2010.
- Paper Review #2. Due February 19th at 9am.
- Problem Set #1. Due February 24th at 9am.
- Problem Set #2. Due March 2nd at 9am.
- Problem Set #3. Due March 11th at 9am.
- Paper Review #3. Due March 9th at 9am.
- Problem Set #4. Due March 20th at 9am.
- Paper Review #4. Due March 20th at 9am.
- Problem Set #5. Due April 6th at 9am.
- Problem Set #6. Due April 13th at 9am.
- Problem Set #7. Due April 20th at 9am.
- Problem Set #8. Due April 27th at 9am.
- Problem Set #9. Due May 4th at 9am.
|
|