OVERVIEW:
- Introduction, Feature extraction - edge, texture, motion (optical flow), others
- Image Segmentation
- Registration
- Tracking & Sequential Detection - Kalman filter & Extensions, Particle filter, Change Detection
- Object Recognition (Image Classification)
- Shape Analysis - Representations, Distances, Segmentation, Tracking
- 3D Scene Reconstruction
- Image formation models (camera models)
- Structure from Motion
- Structure from Stereo (if time permits)
- Shape representations in 3D (if time permits)
DETAILED SYLLABUS: I intend to give basics of each problem, not necessarily state of the art. The goal of the class will be to also learn the underlying techniques from Signal Processing / Math. I will keep putting pointers to latest research for those interested.
Introduction & Feature extraction 3-4 classes
Edge Detection
Texture
Motion - Optical Flow
Segmentation 4 classes
Histogram Mode Finding
Clustering - K-means, Expectation Maximization, Clustering on Intensity and Location
Energy Minimization for Contour Estimation, "Snakes"
Region growing
Contour Tracing after edge filtering
Registration 3 classes
Hough Transform
Learning Affine parameters as a Least Mean Square Error estimation problem, Weighted LS, Recursive LS
Learning Scaled Euclidean parameters - Landmark Shape Analysis
"Deformotion": Joint Segmentation and Registration
Recognition - Face/Object/Activity 3 classes
Likelihood Ratio Testing
PCA, LDA, Subspace LDA, Kernel methods, Discriminant EM
Support Vector Machines
PCNSA
Tracking and Change Detection 3-4 classes
Kalman Filter
Extended Kalman Filter, Gaussian Sum Filter
Particle Filter
Change Detection
Shape Analysis - Landmark shape & Continuous curves 4-5 classes, maybe more
Landmark Shape - Procrustes distance, tangent coordinates
Classification & Registration
Continuous curves:
Finite dim - Fourier descriptors & B-splines
Infinite dim - Level Set Representation
Segmentation using level sets - edge & region based
Shape tracking
3-D Reconstruction 3 classes
Image Formation models (Camera models)
Structure from Motion
Stereo
One or two guest lectures by other faculty working on Image Analysis
EVALUATION: All 3 components below will carry almost equal weight. We will decide after the first class.
1 mid-term exam
2 projects
PROJECTS: One project will require algorithm implementation and testing. The second one can be reading and analyzing algorithms or implementing and analyzing algorithms. You can choose which one to do when. Also note: EVERYONE will do a DIFFERENT project. Two projects can be on the same topic, but specific problems will be different.
Possible Ideas:
Implementation:
Analysis Topics:
Shape Matching, shape distances
3D Shape representations
Solving for Correspondences
Particle filtering algorithms
More to come
REFERENCES: I will keep telling you which chapter to use from which book or will post notes.
For specific topics:
Very detailed reference:
General reference (used for EE528 in Spring 2005)
Also: MATLAB help for Image and Video Processing