- Last name: A-K (BA 1230, TA: Sam Hasinoff)
- Last name: L-Z (BA 1240, TA: Marcus Brubaker)
| Part I: Representing images as 2D arrays of pixels | ||||
| Week 1 | ||||
| Date | Topic | Sub-topic | Readings | Resources |
| Mon, Jan 7 | Introduction | Digital images; camera response function | Sections 1.1-1.2, 2.1, 2.2, 2.4.2 (only paragraph entitled "silicon sensors"), 2.6.2 from Castleman book | To probe further on High Dynamic Range Imaging look at this paper, as well as www.debevec.org. We will cover the paper in more detail in the next lecture. |
| Wed, Jan 9 | The camera response function: definition & computation | Computing camera response functions from images (cont.) | Sections 1 and 2, up to Eq (2), from this paper (Recovering High Dynamic Range Radiance Maps from Photographs by Paul Debevec). As you read the paper, note that film response curve and camera response curve in the case of digital cameras, are one and the same. | |
| Fri, Jan 11 | Tutorial | TBD | ||
| Week 2 | ||||
| Mon, Jan 14 | The camera response function: definition & computation | The camera response function; computing camera response functions from images | The HDRShop home page. Rendering with Natural Light (a movie that uses high-dynamic-range photography to capture outtdoor illumination and re-use it for image synthesis) | |
| Wed, Jan 16 | Pixel components: color and alpha | Color image acquisition; alpha matting and the matting equation | ||
| Fri, Jan 18 | Tutorial | TBD | ||
| Part II: Representing images as continuous 1D and 2D functions | ||||
| Week 3 | ||||
| Mon, Jan 21 | Computing 1D image derivatives | Least-squares polynomial fitting; intensity derivatives | ||
| Wed, Jan 23 | Computing 1D image derivatives (cont.) | Least-squares polynomial fitting and weighted least squares | ||
| Fri, Jan 25 | Tutorial | TBD | ||
| Week 4 | ||||
| Mon, Jan 28 | Tutorial | TBD | ||
| Wed, Jan 30 | Computing 1D image derivatives (cont.) | Application of LS and WLS fitting to estimation of image intensities and 1st & 2nd image derivatives | To run the demo shown in class, unpack the zipfile polydemo.zip | |
| Fri, Feb 1 | Computing 1D image derivatives (cont.) | Robust polynomial fitting using RANSAC; representing and estimating image curves & curve derivatives | ||
| Week 5 | ||||
| Mon, Feb 4 | Representing 2D image curves | Local analysis of curves: the tangent & normal vectors, the moving frame | To run the demo shown in class, unpack the zipfile curvedemo.zip You should run the demo for a variety of fits (LS, WLS, 1st degree, 2nd degree, etc) to see their effect on the estimated curve. | |
| Wed, Feb 6 | Representing 2D image patches | Relation between curvature and the derivatives of the moving frame; local analysis of 2D image patches | ||
| Fri, Feb 8 | Tutorial | TBD | ||
| Week 6 | ||||
| Mon, Feb 11 | Edge detection | Local analysis of 1D and 2D image patches: the Image Gradient; case study: Painterly Rendering | Paper by Litwinowicz on painterly rendering (this is not required reading). | |
| Wed, Feb 13 | Edge detection (cont.) | The Image Laplacian | ||
| Fri, Feb 15 | Tutorial | TBD | ||
| Week 7 | ||||
| Mon, Feb 18 | No class | |||
| Wed, Feb 20 | No class | |||
| Fri, Feb 22 | No tutorial | |||
| Week 8 | ||||
| Mon, Feb 25 | Corner detection | Relation between local shape near extrema and the eigenvectors/eigenvalues of the Hessian; relation between eigenvalues & the trace & determinant of a matrix; localizing edges as zero crossings of the Laplacian; the Lowe feature detector: finding non-cylindrical points through eigenvalue analysis of the Hessian of the Laplacian | Paper by Mortensen on Intelligent Scissors (this is not required reading). This paper and the technique will be covered in one of the forthcoming tutorials. | |
| Wed, Feb 27 | Corner detection (continued) | |||
| Fri, Feb 29 | Tutorial | TBD | ||
| Week 9 | ||||
| Mon, Mar 3 | Template matching and correlation | Representing images as vectors; evaluating similarity using RMS distance error, cross-correlation and normalized cross-correlation; | To run the demo shown in class, unpack the zipfile corrdemo.zip and type corrdemo at the matlab prompt. | |
| Wed, Mar 5 | Template matching and correlation (cont.) | Dimensionality reduction using Principal Component Analysis; representing face images using Eigenfaces | To run the demo shown in class, unpack the zipfile pcademo.zip and type pcademo at the matlab prompt. | |
| Fri, Mar 7 | MIDTERM | |||
| Week 10 | ||||
| Mon, Mar 10 | Principal Component Analysis | Face recognition using Eigenfaces | Section 13.6 from Castleman | To run the demo shown in class, unpack the zipfile recognition_demo.zip and type pca_recdemo at the matlab prompt. |
| Wed, Mar 12 | Principal Component Analysis | Face recognition using Eigenfaces | ||
| Fri, Mar 14 | Tutorial | TBD | ||
| Part IV: Multi-resolution image representations | ||||
| Week 11 | ||||
| Mon, Mar 17 | The convolution operation, Gaussian Pyramids | Definition of convolution; | Original paper by Burt and Adelson on the Gauss/Laplacian pyramids. You should read up to, but not including, section entitled Entropy. | |
| Wed, Mar 19 | Pyramid Blending, Texture synthesis and Morphing | The Beier-Neely morphing algorithm | Paper by Wei and Levoy on Texture Synthesis. This is not required reading. Paper by Burt and Adelson on pyramid blending.Paper by Beier and Neely on Image Morphing | |
| Fri, Mar 21 | Good Friday | |||
| Week 12 | ||||
| Mon, Mar 24 | Polynomial fitting vs. correlation | Analysis of WLS polynomial fitting and image smoothing as a template matching operation; template matching expressed as a multiplication of an image with a Toeplitz matrix; Gaussian image smoothing; The Difference of Gaussians filter and its equivalence to the Image Laplacian; Image differentiation by convolution with Gaussian derivative filters | This Matlab demo shows how a 1D image changes as we smooth it with a sequence of Gaussians of increasing standard deviation | |
| Wed, Mar 26 | The Haar Wavelet Transform | Wavelet compression of 1D and 2D images | A tutorial paper on the Haar Wavelets. | Matlab wavelets demo shown in class. |
| Fri, Mar 28 | Tutorial | TBD | ||
| Week 13 | ||||
| Mon, Mar 31 | The Haar Wavelet Transform (cont.) | Sections 1-3 of paper by David Lowe describing SIFT. | Web page on SIFT (with demo code) | |
| Wed, Apr 2 | Matching images using SIFT | SIFT-based feature detection; the SIFT descriptor; image matching using SIFT | Sections 4-6 from SIFT paper | |
| Fri, Apr 4 | Tutorial | TBD | ||
| Part V: Introduction to 2D Image Transformations | ||||
| Week 14 | ||||
| Mon, Apr 7 | Matching images using SIFT, Intro to homogeneous coordinates | The SIFT descriptor; Homography-based image warping | ||
| Wed, Apr 9 | Image mosaicing | Estimating homographies from point correspondences; the Autostitch algorithm | ||
| Fri, Apr 11 | Tutorial | TBD | ||
Site last modified on Wednesday, May 14, 2008
Send questions or comments about this page to kyros@cs.toronto.edu