Imaging and Deep Learning
Archived 2025 offering. For the current version, see Imaging and Deep Learning (2026).
An introduction to imaging systems and deep learning. Sensor devices capturing energy across the electromagnetic spectrum provide a rich gamut of images that can be processed digitally for applications including medical imaging, surveillance, remote sensing, and consumer electronics.
This course provides fundamental mathematical tools for image analysis, covering sampling, perception, color, Fourier analysis and representation, unitary transforms, noise reduction and restoration, computed tomography, compression, and machine learning for classification and computer vision.
Course materials
- Syllabus
- Introduction to imaging systems
- 1. Image formation
- 2. Imaging spectroscopy for cultural heritage and conservation
- 3. Image enhancement
- 4. Fourier analysis
- 5. Image sampling
- 6. Perception and retina displays
- 7. CMOS sensors and color arrays
- 8. DFT, FFT and filtering
- 9. Deblurring
- 10. X-ray tomography
- 11. Optical coherence tomography (OCT)
- 12. Convolutional neural networks, autoencoders and GANs
- 13. Image compression