Hany Farid, Professor at UC Berkeley

Image understanding: supervised learning: regression: iterative least-squares, steepest descent

Image filtering: pyramids: Gaussian pyramid

Image analysis: motion: feature tracking, implementation

Image formation: pixels: color filter array

Image filtering: features: histogram of gradients (HOG)

Image understanding: unsupervised learning: principal component analysis (PCA): canonical basis

Shadows

Image understanding: unsupervised learning: principal component analysis (PCA): eigenfaces

Image understanding: unsupervised learning: tSNE: implementation

Image understanding: unsupervised learning: expectation/maximization: M-step

Image understanding: unsupervised learning: expectation/maximization: EM

Image understanding: unsupervised learning: principal component analysis (PCA): implementation

Closing: parting thoughts

Image understanding: unsupervised learning: principal component analysis (PCA): computation

Image understanding: supervised learning: regression: iterative least-squares, steepest descent

Human Abilities and Limits

Image understanding: supervised learning: classification: support vector machine: slack variables

Specularities

Reflections

Deepfakes

Image understanding: unsupervised learning: principal component analysis (PCA): eigenvectors

Lighting

Lens Flare

Image understanding: unsupervised learning: expectation/maximization: E-step

3D Modelling

Image formation: pixels: JPEG compression

Image understanding: supervised learning: classification: support vector machine: maximizing margins

Image understanding: supervised learning: classification: support vector machine: nonlinear SVM

Image understanding: supervised learning: classification: support vector machine: linear SVM

Image understanding: supervised learning: classification: artificial neural networks: sigmoid

Image filtering: convolution: separable convolution

Image understanding: unsupervised learning: clustering: k-means implementation

Image understanding: supervised learning: classification: linear: logistic regression

Image understanding: unsupervised learning: expectation/maximization: EM implementation

Variables, data types, expressions, operators: assignment

Image filtering: space and frequency: complex exponential

Image understanding: unsupervised learning: principal component analysis (PCA): covariance matrix

Image filtering: convolution: convolution, 1-D

Image understanding: unsupervised learning: t-distributed stochastic neighbor embedding (tSNE)

Image analysis: stereo: depth from stereo

Image understanding: supervised learning: classification: linear: multiclass classifier

Image understanding: supervised learning: regression: iterative least-squares, gradient descent

Introduction

Image understanding: supervised learning: regression: total least-squares: line fitting

Image understanding: supervised learning: classification: ANN: convolutional

Ballistic Motion

Vanishing Points and Lines

Image analysis: motion: feature tracking

Image understanding: supervised learning: classification: support vector machine: margins