[français]
Charles Deledalle  Teaching
 UCSD ECE285 Machine learning for image processing
 UCSD ECE285 Image and video restoration
 UCSD KPU's Smart IoT Workshop (Summer 2019)
 Miscellaneaous
UCSD ECE285 Machine learning for image processing
Spring 2019 version: click here.
Lectures






Assignments (individual)
 Assignment 0  Python, Numpy and Matplotlib (prereq, optional)
 Assignment 1  Backpropagation
 Assignment 2  CNNs and Pytorch
 Assignment 3  Transfer Learning
 Assignment 4  Image Denoising
 MNIST: dataset, MNISTtools.py
 CaltechUCSDBirds: dataset, train.csv, val.csv
 BSDS: dataset
 nntools package: nntools.py
Projects (pick only one of them, by groups of 3/4)
 Project A  Image Captioning
 Project B  Style Transfer
 Project C  MultiObject detection
 Project D  Openended
Supplemtary meterials
Everything else
 Fall 2019: enroll to Piazza ECE285 MLIP FA19. Access Google Calendar.
 Spring 2019: enroll to Piazza ECE285 MLIP SP19. Access Google Calendar.
 Fall 2018: enroll to Piazza ECE285 MLIP FA18
 Spring 2018: Go to TritonEd
UCSD ECE285 Image and video restoration
Fall 2017 Matlab version: click here.
Lectures
Image sciences, image processing, image restoration, photo manipulation. Image and videos representation. Digital versus analog imagery. Quantization and sampling. Sources and models of noises in digital CCD imagery: photon, thermal and readout noises. Sources and models of blurs. Convolutions and point spread functions. Overview of other standard models, problems and tasks: saltandpepper and impulse noises, half toning, inpainting, superresolution, compressed sensing, high dynamic range imagery, demosaicing. Short introduction to other types of imagery: SAR, Sonar, ultrasound, CT and MRI. Linear and illposed restoration problems. 
Moving averages. Finite differences and edge detectors. Gradient, Sobel and Laplacian. Linear translations invariant filters, crosscorrelation and convolution. Adaptive and nonlinear filters. Median filters. Morphological filters. Local versus global filters. Sigma filter. Bilateral filter. Patches and nonlocal means. Applications to image denoising. 
Fourier decomposition and Fourier transform. Continuous verse discrete Fourier transform. 2D Fourier transform and spectral analysis. Lowpass and highpass filters. Convolution theorem. Image sharpening, Image resizing and subsampling. Aliasing, Nyquist Shannon theorem, zeropadding, and windowing. Spectral models of subsampling in CT and MRI. Radon transform, kspace trajectories, and streaking artifacts. 
Heat equation. Discretization and finite difference. Explicit and implicit Euler schemes. CFL conditions. Continuous Gaussian convolution solution. Linear and nonlinear scale spaces. Anisotropic diffusion. PeronaMalik and Weickert model. Variational methods. Tikhonov regularization by gradient descent. Links between variational models and diffusion models. TotalVariation regularization and ROF model. Sparsity and group sparsity. Applications to image deconvolution. 
Sample mean, law of large numbers, and method of moments. Mean square error and biasvariance tradeoff. Unbiased estimation: MVUE, CramèrRaoBound, Efficiency, MLE. Linear estimation: BLUE, GaussMarkov theorem, leastsquare error estimator, MoorePenrose pseudoinverse. Bayesian estimators: likelihood and priors, MMSE and posterior mean, MAP. Linear MMSE, applications to Wiener deconvolution, image filtering with PCA, and the nonlocal Bayes algorithm. Applications to image denoising. 
Limits of Wiener filtering. Nonlinear shrinkage functions. Limits of Fourier representation. Continuous and discrete wavelet transforms. Sparsity and shrinkage in wavelet domain. Undecimated wavelet transforms, a trous algorithm. Regularization. Sparse regression, combinatorial optimization and matching pursuit. LASSO, nonsmooth optimization, and proximal minimization. Link with implicit Euler scheme. ISTA algorithm. Synthesis versus analysis regularized models. Applications to image deconvolution. 
Patch models and sparse decompositions of image patches. Dictionary learning and the kSVD algorithm. Collaborative filtering and BM3D. Nonlocal sparse based models. Expected patch loglikelihood. Other applications of patch models in inpainting, superresolution and deblurring. 
Assignments in Python (individual)
 Assignment 0  Python, Numpy and Matplotlib (prereq, optional)
 Assignment 1  Watermarking
 Assignment 2  Basic Image Tools
 Assignment 3  Basic Filters
 Assignment 4  Nonlocal means
 Assignment 5  Fourier transform
 Assignment 6  Wiener deconvolution
 Archive: ece285_IVR_assignments.zip
Projects in Python (pick only one of them, by groups of 2/3)
 Project A  Anisotropic Diffusion
 Project B  TotalVariation
 Project C  Wavelets
 Project D  Nonlocal regularization
Everything else
 Spring 2019: enroll to Piazza ECE285 MLIP SP19. Access Google Calendar.
Miscellaneaous
 Submitting Notebook to Gradescope as PDF
 Setting up Python and Jupyter with Conda environments on Linux or Max OSX
 Setting up Python, PyTorch and Jupyter on Windows
 Transferring files from and to an UCSD's DSMLP Pod session
 On the convergence of gradient descent
 Cookbook for data scientists
 Documentation for Git: https://www.atlassian.com/git/tutorials
Last modified: Wed Oct 30 04:50:58 Europe/Berlin 2019