Computer Vision
2004-05
Lecturer: Dr John Daugman
Taken by: Part II
Prerequisite course: Continuous Mathematics
Aims
The aims of this course are to introduce the principles, models and
applications of computer vision, as well as some mechanisms used in
biological visual systems that may inspire design of artificial ones.
The course will cover: image formation, structure, and coding;
edge and feature detection; neural operators for image analysis;
texture, colour, stereo, and motion; wavelet methods in vision;
interpretation of surfaces, solids, and shapes; data fusion;
visual inference and learning; and approaches to face recognition.
Lectures
- Goals of computer vision; why they are so difficult.
How images are formed, and the ill-posed problem of
making 3D inferences from them about objects and their
properties.
- Image sensing, pixel arrays, CCD cameras, framegrabbers.
Elementary operations on image arrays; coding and information measures.
- Biological visual mechanisms from retina to cortex.
Photoreceptor sampling; receptive field profiles; spike train coding;
channels and pathways. Neural image encoding operators.
- Mathematical operators for extracting image structure.
Finite differences and directional derivatives.
Filters; convolution; correlation. 2D Fourier domain theorems.
- Edge detection operators; the information revealed by edges.
The Laplacian operator and its zero-crossings. Logan's Theorem.
- Scale-space, multi-resolution representations, causality.
Wavelets as visual primitives.
- Higher level visual operations in brain cortical areas.
Multiple parallel mappings; streaming and divisions of labour;
reciprocal feedback through the visual system.
- Texture, colour, stereo, and motion descriptors.
Disambiguation and the achievement of invariances.
- Lambertian and specular surfaces.
Reflectance maps. Discounting the illuminant when
infering 3D structure and surface properties.
- Inferring shape from shading: surface geometry.
Boundary descriptors; Fundamental Theorem of Curves; codons.
- Perceptual psychology and visual cognition. Vision
as model-building and graphics in the brain. Learning to see.
- Lessons from neurological trauma and visual deficits.
Visual illusions and what they may imply about how vision works.
- Bayesian inference in vision; knowledge-driven
interpretations. Classifiers. Probabilistic methods in vision.
- Object-centred coordinates.
Solid parameterisation and superquadrics.
Appearance-based {\em versus} volumetric model-based vision.
- Vision as a set of inverse problems; mathematical methods
for solving them: energy minimisation,
relaxation, regularisation.
- Approaches to face detection, face recognition, and facial interpretation.
Objectives
At the end of the course students should
- understand visual processing from both "bottom-up" (data oriented) and
"top-down" (goals oriented) perspectives
- be able to decompose visual tasks into sequences of image analysis
operations, representations, specific algorithms, and inference principles
- understand the roles of image transformations and their invariances
in pattern recognition and classification
- be able to analyse the robustness, brittleness, generalisability,
and performance of different approaches in computer vision
- be able to describe key aspects of how biological visual systems
encode, analyse, and represent visual information
- be able to think of ways in which biological visual strategies might be
implemented in machine vision, despite the enormous differences in hardware
- understand in depth at least one major practical application problem,
such as face recognition, detection, and interpretation
Reference books
Shapiro L and Stockman G (2001). Computer Vision.
(Prentice Hall: ISBN 0-13-030796-3)
Duda R O, Hart P E, and Stork D G (2001). Pattern Classification,
2nd ed. (Wiley: ISBN 0-471-05669-3)
- Syllabus
- Lecture Notes
-
Learning Guide, Lecture Summary, and Worked Examples
- Past
exam questions
- Assignments from the Learning Guide:
- (3 Feb 2005): Exercises 2, 4, and 7.
Please also experiment with the (Matlab-based) Groningen image analysis tool which is
available at http://matlabserver.cs.rug.nl/,
using the L2 norm and either your own images or those on the site. (The web-browser
Explorer works better with this than Netscape.)
- (10 Feb 2005): Exercises 5, 10, and 11.
- (17 Feb 2005): Exercises 1 and 8. Also study this compelling
lightness illusion, and this compelling
motion illusion, and try to explain them!
Here are other dynamic brightness illusions.
- (24 Feb 2005): Exercises 13 and 14.
Part of this lecture will be an Examples Class, to
review the questions set thus far from the Learning Guide.
- (3 March 2005): Exercises 6, 9 and 12.
- (10 March 2005): Supplementary Review and Examples Class.
Other resources on-line
|
