*Computer Vision*

2001-02

**Lecturer:** Dr John Daugman (jgd1000@cl.cam.ac.uk)

*No. of lectures:* 8

*Prerequisite course: Continuous Mathematics*

#### Aims

The aims of this course are to introduce the principles, models and
applications of computer vision. The course will cover image structure
and encoding; edge and feature detection; interpretation of surfaces;
texture, colour, stereo, and motion; wavelet methods in vision;
parameterisations for solids and shapes; visual inference; and
strategies for automatic face recognition.
#### Lectures

- Overview.
Goals of computer vision; why they are so difficult.
Image sensing, pixel arrays, CCD cameras, framegrabbers.

- Sampling theory.
Finite differences and directional derivatives.
Filtering; 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. Texture, colour, stereo, and motion descriptors.
Disambiguation.

- Lambertian and specular surfaces.
Reflectance maps. Bayesian inference in vision; knowledge-driven
interpretations.

- Inferring shape from shading: surface geometry.
Boundary descriptors; Fundamental Theorem of Curves; codons.

- Object-centred coordinates.
Solid parameterisation. Superquadrics. Inverse problems; energy
minimisation, relaxation, regularisation.

- Model-based vision.
Appearance-based
*versus* volumetric models. Applications and
case studies. Face recognition.

#### 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

#### Reference book

Shapiro, L., and Stockman, G. (2001). *Computer Vision*.
Prentice Hall.

**Lecturer:** Dr John Daugman (jgd1000@cl.cam.ac.uk)

**Taken by:** Part II, Part II (General), Diploma

**Number of lectures:** 8

**Lecture location:** Large Lecture Theatre

**Lecture times:** 12:00 on TT starting 25-Apr-02

**
**