Image Processing and Analysis

Dr. Stan Birchfield conducts research and development at Microsoft® Corporation, working on various aspects of robotics and computer vision. Previously, he was an assistant professor, then associate professor in the Electrical and Computer Engineering Department of Clemson University, where he spent a decade conducting research and teaching. He remains an adjunct faculty member at Clemson. He received a Ph.D. in Electrical Engineering with a minor in Computer Science from Stanford University in 1999, an M.S. from Stanford in 1996, and a B.S. from Clemson in 1993. While at Stanford, his research was supported by a National Science Foundation Graduate Research Fellowship, and he was part of the team that won first place at the AAAI Mobile Robotics Competition of 1994. After graduating from Stanford, he spent four years as a research engineer at a startup company in Palo Alto, California. At Clemson he co-founded a startup that uses computer vision to automatically collect aggregate traffic parameters from live video feeds. Over the years he has worked with or consulted for various companies, including Sun Microsystems, SRI International, Canon, Microsoft, and Autodesk. Dr. Birchfield has authored or co-authored more than 70 publications in the areas of computer vision, stereo correspondence, visual tracking, spatial acoustics, and mobile robotics, and his open-source software has been used by thousands of researchers around the world.

1. INTRODUCTION.
Image processing and analysis. History and related fields. Sample applications. Image basics. Looking forward. Further reading. Problems.
2. FUNDAMENTALS OF IMAGING.
Vision in nature. Image formation. Image acquisition. Other imaging modalities. A detailed look at electromagnetic radiation. Further reading. Problems.
3. POINT AND GEOMETRIC TRANSFORMATIONS.
Simple geometric transformations. Graylevel transformations. Graylevel histograms. Multi-spectral transformations. Multi-image transformations. Change detection. Compositing. Interpolation. Warping. Further reading. Problems.
4. BINARY IMAGE PROCESSING.
Morphological operations. Labeling regions. Computing distance in a digital image. Region properties. Skeletonization. Boundary representations.
5. SPATIAL-DOMAIN FILTERING.
Convolution. Smoothing by convolving with a Gaussian. Computing the first derivative. Computing the second derivative. Nonlinear filters. Grayscale morphological operators. Further reading. Problems.
6. FREQUENCY-DOMAIN PROCESSING.
Fourier transform. Discrete Fourier transform (DFT). Two-dimensional DFT. Frequency-domain filtering. Localizing frequencies in time. Discrete wavelet transform (DWT). Further reading. Problems.
7. EDGES AND FEATURES.
Multiresolution processing. Edge detection. Approximating intensity edges with polylines. Feature detectors. Feature descriptors. Further reading. Problems.
8. COMPRESSION.
Basics. Lossless compression. Lossy compression. Compression of videos. Further reading. Problems.
9. COLOR.
Physics and psychology of color. Trichromacy. Designating colors. Linear color transformations. Color spaces. Further reading. Problems.
10. SEGMENTATION.
Thresholding. Deformable models. Image segmentation. Graph-based methods. Further reading. Problems.
11. MODEL FITTING
Fitting curves. Fitting point cloud models. Robustness to noise. Fitting multiple models. Further reading. Problems.
12. CLASSIFICATION.
Fundamentals. Statistical pattern recognition. Generative methods. Discriminative methods. Further reading. Problems.
13. STEREO AND MOTION.
Human stereopsis. Matching stereo images. Computing optical flow. Projective geometry. Camera calibration. Geometry of multiple views. Further reading. Problems.