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.
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
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.
Book by Haar Romeny Bart M
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.
EUR 10,42 per la spedizione da Regno Unito a Italia
Destinazione, tempi e costiDa: Ria Christie Collections, Uxbridge, Regno Unito
Condizione: New. In. Codice articolo ria9781402015076_new
Quantità: Più di 20 disponibili
Da: moluna, Greven, Germania
Kartoniert / Broschiert. Condizione: New. A breakthrough in interactive teaching of multi-scale methods for image analysis For Mathematica 5.0 an upgrade is available for free download. A breakthrough in interactive teaching of multi-scale methods for image analysisFor M. Codice articolo 458473217
Quantità: Più di 20 disponibili
Da: Lucky's Textbooks, Dallas, TX, U.S.A.
Condizione: New. Codice articolo ABLIING23Mar2411530141876
Quantità: Più di 20 disponibili
Da: AHA-BUCH GmbH, Einbeck, Germania
Taschenbuch. Condizione: Neu. Neuware - Many approaches have been proposed to solve the problem of finding the optic flow field of an image sequence. Three major classes of optic flow computation techniques can discriminated (see for a good overview Beauchemin and Barron IBeauchemin19951): gradient based (or differential) methods; phase based (or frequency domain) methods; correlation based (or area) methods; feature point (or sparse data) tracking methods; In this chapter we compute the optic flow as a dense optic flow field with a multi scale differential method. The method, originally proposed by Florack and Nielsen [Florack1998a] is known as the Multiscale Optic Flow Constrain Equation (MOFCE). This is a scale space version of the well known computer vision implementation of the optic flow constraint equation, as originally proposed by Horn and Schunck [Horn1981]. This scale space variation, as usual, consists of the introduction of the aperture of the observation in the process. The application to stereo has been described by Maas et al. [Maas 1995a, Maas 1996a]. Of course, difficulties arise when structure emerges or disappears, such as with occlusion, cloud formation etc. Then knowledge is needed about the processes and objects involved. In this chapter we focus on the scale space approach to the local measurement of optic flow, as we may expect the visual front end to do. 17. 2 Motion detection with pairs of receptive fields As a biologically motivated start, we begin with discussing some neurophysiological findings in the visual system with respect to motion detection. Codice articolo 9781402015076
Quantità: 2 disponibili