Exploring difference between color spaces and color-based image segmentation. Experiments with edge detection.
Exploring different feature spaces - using Fourier shape descriptors, experimenting with wavelet transform, template matching.
Using and interpretation of ROC curves, experiments with PCA and ICA.
Estimating and sampling from densities, learning video background models, building a simple object tracker.
Using LDA for image analysis. Experiments with Support Vector Machines.
Image segmentation with K-means, EM and hierarchical clustering algorithms.
Oral Presentation Paper Topic Examples
Comparison of low-level features for object recognition
Final Project Examples
Final projects included implementation and experiments with existing pattern recognition as applied to computer vision problems. Examples of past successful projects:
- Efficient tracking algorithm learning object appearance
- System that tracks fast moving baseball in video
- Soda can recognition on an iPaq
- Experiments with multi-class boosting cascade
- Video camera-based mouse device