EECS225B, Fall 2022
Digital Image Processing
Tuesdays and Thursdays, 11:00am-12:30pm
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: Thursdays 12:30pm-1:30pm
TA:
Meng Wei
meng_wei@berkeley.edu
Office Hours: Wednesdays 3pm-4pm
|
|
Zoom Videos for Online lecttures:
- Passcode on bcoursesVideo August 30
- Passcode on bcoursesVideo September 1
- Passcode on bcoursesVideo September 6
- Passcode on bcoursesVideo September 8
- Passcode on bcoursesVideo September 13
- Passcode on bcoursesVideo September 15
- Passcode on bcoursesVideo September 20
- Passcode on bcoursesVideo September 22
- Passcode on bcoursesVideo September 27
- Passcode on bcoursesVideo September 29
- Passcode on bcoursesVideo October 4
- Passcode on bcoursesVideo October 6
- Passcode on bcoursesVideo October 11
- Passcode on bcoursesVideo October 13_1
- Passcode on bcoursesVideo October 13_2
- Passcode on bcoursesVideo October 18
- Passcode on bcoursesVideo October 20
- Passcode on bcoursesVideo October 25
- Passcode on bcoursesVideo November 1
- Passcode on bcoursesVideo November 3
- Passcode on bcoursesVideo November 8
- Passcode on bcoursesVideo November 10
- Passcode on bcoursesVideo November 15
- Passcode on bcoursesVideo November 17
- Passcode on bcoursesVideo November 22
- Passcode on bcoursesVideo November 29
- Passcode on bcoursesVideo December 1
Recommended Books:
- Prof. Hany Farid's notes on Fundamentals of Image Processing. PDF Video
- 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:
- Fundamentals of Digital Image and Video Processing
- Image and Video Processing: From Mars to Hollywood with a Stop at the Hospital
- 22 videos on deep learning for computer vision, Justin Johnson, University of Michigan
Deep learning Restoration and Enhancement papers from ICIP 2022:
- IMAGE DEBLURRING USING DEEP MULTI-SCALE DISTORTION PRIOR
- DEEP IMAGE DEBANDING
- ATTENTION-BASED NEURAL NETWORK FOR ILL-EXPOSED IMAGE CORRECTION
- A NEW REGULARIZATION FOR RETINEX DECOMPOSITION OF LOW-LIGHT IMAGES
- SVBR-NET: A NON-BLIND SPATIALLY VARYING DEFOCUS BLUR REMOVAL NETWORK
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 paper reviews or Python/Matlab programming assignments. Homework will be graded, and will contribute 60% to the final grade, where 10% is for reading assignments and 50 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 October. 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.
|
-
Welcome to EE225B!
-
Please sign up for the class piazza page at this link: piazza.com/berkeley/fall2022/eecs225b
-
Thu. Aug. 25, 2022.
Lecture 1: Introduction
-
Tue. Aug. 30, 2022.
Lecture 2: Modalities of Images Capture
-
Thu Sept. 1, 2022.
Lecture 3: human-perception.
-
Tue Sep.6, 2022
Lecture 4: Neural Networks.
-
Thu Sep.8, 2022
Lecture 5: Neural Networks.
-
Tue Sep.13, 2022
Lecture 6: Neural Networks.
-
Thu Sep.15, 2022
Lecture 7: Intensity Transformation and spatial Filtering.
-
Tue Sep.27, 2022
Lecture 10: Filtering in the Frequency Domain.
-
Thu Oct.6, 2022
Lecture 13: Image Restoration.
-
Thu Oct.13, 2022
Lecture 15_1: weiner-filter .
Lecture 15_2: Random Processes .
Lecture 15_3: Image Restoration .
-
Tue Nov.1, 2022
Lecture 19: Basics of image coding.
-
Thu Nov.3, 2022
Lecture 20: MethodsofBitAssignment.
-
Tue Nov.8, 2022
Lecture 21: TransformImageCoding.
-
Thu Nov.10, 2022
Lecture 22: Restoration.
-
Tue Nov.15, 2022
Lecture 23_1: Lossy image compression .
Lecture 23_2: combined-transsform-block-coding .
-
Thu Nov.17, 2022
Lecture 24: Pyramid .
-
Tue Nov.29, 2022
Lecture 27: combined-lustig-wavelet .
Lecture 27: Tilin_of_th_time_frequency_plane .
Lecture 27: ee123handoutTF-gastpar .
-
Thu Dec.1, 2022
Lecture 28: ill-conditioned-algorithm-problem .
-
- Reading Assignment #1. Due Thursday September 8nd at 9am.
- Problem Set #1. Due Thursday September 15th at 9am.
- Reading Assignment #2. Due Thursday September 22th at 9am.
- Problem Set #2. Due Thurday October 4th at 9am.
Reading Assignment #3. Due Tuesday October 11th at 9am.
Problem Set #3. Due October 13th at 11am.
Reading Assignment #4. Due Thursday October 20th at 11am.
Problem Set #4. Due October 27th at 11am.
Problem Set #5. Due November 1st at 11am.
Problem Set #6. Due November 17th at 11am.
Problem Set #7. Due November 24th at 11am.
Problem Set #8. Due December 7th at 11am.
Optional Problem Set #9. Due December 11th at 11am.
|
|