Front-End Vision and Multi-Scale Image Analysis: Multi-Scale Computer Vision Theory and Applications, Written in Mathematica

Front-End Vision and Multi-Scale Image Analysis is a tutorial in multi-scale methods for computer vision and image processing. It builds on the cross fertilization between human visual perception and multi-scale computer vision (`scale-space') theory and applications. The multi-scale strategies recognized in the first stages of the human visual system are carefully examined, and taken as inspiration for the many geometric methods discussed. All chapters are written in Mathematica, a spectacular high-level language for symbolic and numerical manipulations. The book presents a new and effective approach to quickly mastering the mathematics of computer vision and image analysis. The typically short code is given for every topic discussed, and invites the reader to spend many fascinating hours `playing' with computer vision. Front-End Vision and Multi-Scale Image Analysis is intended for undergraduate and graduate students, and all with an interest in computer vision, medical imaging, and human visual perception.

Front-End Vision and Multi-Scale Image Analysis. The purpose of this book. Scale-space theory is biologically motivated computer vision. This book has been written in Mathematica. Acknowledgements. 1: Apertures and the notion of scale. 2: Foundations of scale-space. 3: The Gaussian Kernel. 4: Gaussian derivatives. 5: Multi-scale derivatives: implementations. 6: Differential structure of images. 7: Natural limits on observations. 8: Differentiation and regulation. 9: The front-end visual system - the retina. 10: A scale-space model for the retinal sampling. 11: The front-end visual system LGN and cortex. 12: The front-end visual system - cortical columns. 13: Deep structure I. Watershed segmentation. 14: Deep structure II. Catastrophe theory. 15: Deep structure III. 16: Deblurring Gaussian blur. 17: Multi-scale optic flow. 18: Color differential structure. 19: Steerable kernels. 20: Scale-time. 21: Geometry-driven diffusion. 22: Epilog. A: Introduction to Mathematica. A.1. Quick overview of using Mathematica. A.2. Quick overview of the most useful commands. A.3. Pure functions. A.4. Pattern matching. A.5. Some special plot forms. A.6. A faster way to read binary 3-D data. A.7. What often goes wrong. A.8. Suggested reading. A.9. Web resources. B: The concept of convolution. B.1. Convolution. B.2. Convolution is a product in the Fourier domain. C: Installing the book and packages. C.1. Content. C.2. Installation for all systems. C.3. Viewing the book in the help browser. C.4. Sources of additional applications. D: First start with Mathematica: Tips and tricks. D.1. Evaluation. D.2. Images. D.3. Programming. D.4. 3-D. References. Index.