CSC320W: Introduction to Visual Computing
Schedule and Notes
Lectures: W 6-8 pm (BA1190)
Tutorials W 8 pm
Part I: Representing images as 2D arrays of pixels
Week 1
Wed, Jan 8    Introduction; The Camera Response Function Digital images; computing camera response functions from images.
Slides: [Printer friendly] [Color]   
Sections 1.1-1.2, 2.1, 2.2, 2.4.2 (only paragraph entitled "silicon sensors"), 2.6.2 from Castleman book; Sections 1 and 2, up to Eq (2), from paper. 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.    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)   
No tutorial during week 1.       
Fri, Jan 10    Assignment Assignment 1 is out, due January 27.   
Week 2
Wed, Jan 15    Pixel components: color and alpha     Color image acquisition; alpha matting and the matting equation   
Slides: [pdf]
Tutorial    Matting and linear equations   
Part II: Representing images as continuous 1D and 2D functions
Week 3
Wed, Jan 22    Computing 1D image derivatives    Least-squares polynomial fitting; intensity derivatives; weighted least squares; RANSAC   
Slides: [pdf]
Polynomial fitting demo to be shown in next week's tutorial:
If you download it, run it for a variety of fits (LS, WLS, 1st degree, 2nd degree, etc) to see their effect.   
Tutorial    Questions about Assignment 1   
Week 4
Mon, Jan 27    Assignment Assignment 1 due at 11:59pm.    Worth 10% of the final mark.
Wed, Jan 29    Representing 2D image curves    Local analysis of curves: the tangent & normal vectors, the moving frame   
Slides: [pdf]
To run the demo shown in class, unpack the zipfile
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.   
Tutorial    Polynomial fitting and 2D curves    Tutorial notes on polynomial fitting and 2D curves by Micha Livne.   
Week 5
Wed, Feb 5    Edge detection    Local analysis of 1D and 2D image patches: the Image Gradient. Case study: Painterly Rendering   
Slides: [pdf]
Paper by Litwinowicz on painterly rendering (this is not required reading).   
Tutorial    Description of A2, Questions and answers about Assignment 1, part B [slides], and Paper on Accidental Pinhole and Pinspeck cameras (this is not required reading).   
Fri, Feb 7    Assignment Assignment 2 is out, due March 2 (two days later than originally advertised!).   
Week 6
Wed, Feb 12    Corner detection, Intelligent Scissors    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   
Slides: [pdf]
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.   
Tutorial    Questions about Assignment 2 and a paper on Object Recognition by Pedro F. Felzenszwalb. [slides]   
Week 7
Wed, Feb 19    No lecture    Reading week
No tutorial   
Part III: Multi-resolution image representations
Week 8
Wed, Feb 26    Template matching and correlation    Representing images as vectors; evaluating similarity using RMS distance error, cross-correlation and normalized cross-correlation;
Slides: [pdf]    
To run the demo shown in class, unpack the zipfile
  and type corrdemo at the matlab prompt.   
Tutorial    TBD   
Sun, Mar 02    Assignment Assignment 2 due at 11:59pm.    Worth 10% of the final mark.
Week 9
Wed, Mar 5    Principal Component Analysis    Face recognition using Eigenfaces
Slides: [pdf]    
Section 13.6 from Castleman    To run the demo shown in class, unpack the zipfile
  and type pca_recdemo at the matlab prompt.   
Midterm    BA 1190, 6 pm     Worth 20% of the final mark
Wed, Mar 5    Assignment Assignment 3 is out, due March 19.   
Part IV: Alternative image representations
Week 10
Wed, Mar 12    Gaussian Pyramids The idea of representing an image at multiple resolutions is described and studied using Gaussian and Laplacian Pyramids.
Slides: [pdf]
Original paper by Burt and Adelson on the Gauss/Laplacian pyramids. You should read up to, but not including, section entitled Entropy.    This Matlab demo shows how a 1D image changes as we smooth it with a sequence of Gaussians of increasing standard deviation   
Tutorial    TBD   
Week 11
Wed, Mar 19    The Haar Wavelet Transform    Wavelet compression of 1D and 2D images
Slides: [pdf]    
A tutorial paper on the Haar Wavelets.    Matlab wavelets demo shown in class.   
Wed, Mar 19    Assignment Assignment 3 due at 11:59pm.    Worth 10% of the final mark.
Wed, Mar 19    Assignment Assignment 4 is out, due April 2.   
Tutorial    PCA, a few theoretical details.
Week 12
Wed, Mar 26    Polynomial fitting vs. correlation; Matching images using SIFT    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; SIFT-based feature detection; the SIFT descriptor; image matching using SIFT
Slides: [pdf]    
Sections 1-3 of paper by David Lowe describing SIFT.    Web page on SIFT (with demo code)   
Tutorial    On Morphing
Slides: [pdf]    
Part V: Introduction to 2D Image Transformations
Week 13
Wed, Apr 2    Homogeneous coordinates    Homography-based image warping
Slides: [pdf]    
Tutorial    TBD   
Wed, Apr 4    Assignment Assignment 4 due at 11:59pm.    Worth 10% of the final mark.
Apr 9-30    Final Exam    Location, time and date to be announced     Worth 40% of the final mark