This course introduces many standard computer vision problems and computational approaches for solving them. The context of image analysis provides an intuitive and stimulating visual environment for developing and understanding numerical algorithms. A tentative list of topics is given below.
tentative list of topics
- Overview of Imaging Modalities: photo (camera model), video, medical, etc.
- Elements of Image Pre-Processing (gamma and window/center correction, histogram equalization)
- Features and Filtering: colors, edges, corners, SIFT, etc.
- Quantization. Clustering techniques.
- mean-shift, K-means, kernel methods
- Image Segmentation, Shape Reconstruction
- background subtraction, photo/video editing, medical image analysis, interactive segmentation
- basic methods: thresholding, region growing
- clustering methods (eg. RGBXY features)
- regularization methods: shape priors, graph algorithms
- 3D shape reconstruction (medical volumes, multi-view photometric data)
- Image Warping
- domain transformations, homographies
- Model Estimation
- color models: non-parametric (histograms, kernel densities), parametric (Gaussian, GMM), ML estimation, segmentation with color models
- geometric models (lines, planes, homographies) for reconstruction (panoramas, 3D structure),
robust estimation (RANSAC)
- multi-model fitting (multi-structure reconstruction), joint fitting and segmentation
- Correspondence and Registration
- template matching, image registration (SSD, normalized correlation, mutual information)
- non-rigid registration, pictorial structures (pose estimation), stereo, motion, aperture problem
- General Image Labeling and Regularization
- restoration, stitching, scene understanding, stereo, motion, etc.
- robust regularization, optimization algorithms
- Elements of Object Detection
- faces, pedestrians