Computer Vision, Descriptive Geometry, and Classical Mechanics
نویسنده
چکیده
The medial-axis transform, also called skeleton, is a shape abstraction proposed by computer vision. The concept is closely related to cyclographic maps, a tool developed by descriptive geometry to investigate distance functions, and to the solu tion of the eikonal equation. We discuss these connections and their implications on techniques for computing the skeleton.
منابع مشابه
Descriptive Geometry Meets Computer Vision — the Geometry of Multiple Images
The geometry of multiple images has been a standard topic in Descriptive Geometry and Photogrammetry (Remote Sensing) for more than 100 years. During the last twenty years great progress has been made within the field of Computer Vision, a topic with the main goal to endow a computer with a sense of vision. The previously graphical or mechanical methods of reconstruction have been replaced by m...
متن کاملA Geometry Preserving Kernel over Riemannian Manifolds
Abstract- Kernel trick and projection to tangent spaces are two choices for linearizing the data points lying on Riemannian manifolds. These approaches are used to provide the prerequisites for applying standard machine learning methods on Riemannian manifolds. Classical kernels implicitly project data to high dimensional feature space without considering the intrinsic geometry of data points. ...
متن کامل1 . New Algebraic Tools for Classical Geometry †
Classical geometry has emerged from efforts to codify perception of space and motion. With roots in ancient times, the great flowering of classical geometry was in the 19th century, when Euclidean, non-Euclidean and projective geometries were given precise mathematical formulations and the rich properties of geometric objects were explored. Though fundamental ideas of classical geometry are per...
متن کاملLearning shape correspondence with anisotropic convolutional neural networks
Convolutional neural networks have achieved extraordinary results in many computer vision and pattern recognition applications; however, their adoption in the computer graphics and geometry processing communities is limited due to the non-Euclidean structure of their data. In this paper, we propose Anisotropic Convolutional Neural Network (ACNN), a generalization of classical CNNs to nonEuclide...
متن کاملCanonical Correlation Analysis on Riemannian Manifolds and Its Applications
Canonical correlation analysis (CCA) is a widely used statistical technique to capture correlations between two sets of multi-variate random variables and has found a multitude of applications in computer vision, medical imaging and machine learning. The classical formulation assumes that the data live in a pair of vector spaces which makes its use in certain important scientific domains proble...
متن کامل