Lecturer: Dr J.G. Daugman (jgd1000@cl.cam.ac.uk)
No. of lectures: 8
Prerequisite course: Continuous Mathematics
Goals of computer vision and 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 and spectral maps.
Bayesian inference in vision; knowledge-driven interpretations.
Inferring shape from shading: image-formation geometry.
Boundary descriptors; Fundamental Theorem of Curves; codons.
Object-centred coordinates. Solid parameterization. Superquadrics.
Inverse problems. Energy minimization, relaxation, regularization.
Model-based vision. Appearance-based versus volumetric models.
Applications and case studies: face recognition, character recognition.
Reference book:
Jain, R., Kasturi, R., & Schunck, B.G. (1995). Machine Vision. McGraw-Hill.