Восстановить пароль
FAQ по входу

Bigun J. Vision with Direction. A Systematic Introduction to Image Processing and Computer Vision

  • Файл формата pdf
  • размером 7,00 МБ
  • Добавлен пользователем , дата добавления неизвестна
  • Отредактирован
Bigun J. Vision with Direction. A Systematic Introduction to Image Processing and Computer Vision
Издательство Springer, 2006, -395 pp.
Image analysis is a computational feat which humans show excellence in, in comparison with computers. Yet the list of applications that rely on automatic processing of images has been growing at a fast pace. Biometric authentication by face, fingerprint, and iris, online character recognition in cell phones as well as drug design tools are but a few of its benefactors appearing on the headlines.
This is, of course, facilitated by the valuable output of the resarch community in the past 30 years. The pattern recognition and computer vision communities that study image analysis have large conferences, which regularly draw 1000 participants. In a way this is not surprising, because much of the human-specific activities critically rely on intelligent use of vision. If routine parts of these activities can be automated, much is to be gained in comfort and sustainable development. The research field could equally be called visual intelligence because it concerns nearly all activities of awake humans. Humans use or rely on pictures or pictorial languages to represent, analyze, and develop abstract metaphors related to nearly every aspect of thinking and behaving, be it science, mathematics, philosopy, religion, music, or emotions.
The present volume is an introductory textbook on signal analysis of visual computation for senior-level undergraduates or for graduate students in science and engineering. My modest goal has been to present the frequently used techniques to analyze images in a common framework–directional image processing. In that, I am certainly influenced by the massive evidence of intricate directional signal processing being accumulated on human vision. My hope is that the contents of the present text will be useful to a broad category of knowledge workers, not only those who are technically oriented. To understand and reveal the secrets of, in my view, the most advanced signal analysis system of the known universe, primate vision, is a great challenge. It will predictably require cross-field fertilizations of many sorts in science, not the least among computer vision, neurobiology, and psychology.
The book has five parts, which can be studied fairly independently. These studies are most comfortable if the reader has the equivalent mathematical knowledge acquired during the first years of engineering studies. Otherwise, the lemmas and theorems can be read to acquire a quick overview, even with a weaker theoretical background. Part I presents briefly a current account of the human vision system with short notes to its parallels in computer vision. Part II treats the theory of linear systems, including the various versions of Fourier transform, with illustrations from image signals. Part III treats single direction in images, including the tensor theory for direction representation and estimation. Generalized beyond Cartesian coordinates, an abstraction of the direction concept to other coordinates is offered. Here, the reader meets an important tool of computer vision, the Hough transform and its generalized version, in a novel presentation. Part IV presents the concept of group direction, which models increased shape complexities. Finally, Part V presents the grouping tools that can be used in conjunction with directional processing. These include clustering, feature dimension reduction, boundary estimation, and elementary morphological operations. Information on downloadable laboratory exercises (in Matlab) based on this book is available at the homepage of the author (http://www.hh.se/staff/josef).
Part I Human and Computer Vision
Neuronal Pathways of Vision
Part II Linear Tools of Vision
Discrete Images and Hilbert Spaces
Continuous Functions and Hilbert Spaces
Finite Extension or Periodic Functions—Fourier Coefficients
Fourier Transform—Infinite Extension Functions
Properties of the Fourier Transform
Reconstruction and Approximation
Scales and Frequency Channels
Part III Vision of Single Direction
Direction in 2D
Direction in Curvilinear Coordinates
Direction in ND, Motion as Direction
World Geometry by Direction in N Dimensions
Part IV Vision of Multiple Directions
Group Direction and N-Folded Symmetry
Part V Grouping, Segmentation, and Region Description
Reducing the Dimension of Features
Grouping and Unsupervised Region Segregation
Region and Boundary Descriptors
  • Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.
  • Регистрация