Tensor Voting [electronic resource] : A Perceptual Organization Approach to Computer Vision and Machine Learning / by Philippos Mordohai, Gérard Medioni.
- 作者： Mordohai, Philippos. author.
- 其他作者：
- 其他題名：
- Synthesis Lectures on Image, Video, and Multimedia Processing,
- 出版： Cham : Springer International Publishing :Imprint: Springer 2006.
- 叢書名： Synthesis Lectures on Image, Video, and Multimedia Processing,
- 主題： Engineering. , Electrical engineering. , Signal processing. , Technology and Engineering. , Electrical and Electronic Engineering. , Signal, Speech and Image Processing .
- 版本：1st ed. 2006.
- ISBN： 9783031022425
- URL：
Electronic resource
-
讀者標籤：
- 系統號： 005282066 | 機讀編目格式
館藏資訊
This lecture presents research on a general framework for perceptual organization that was conducted mainly at the Institute for Robotics and Intelligent Systems of the University of Southern California. It is not written as a historical recount of the work, since the sequence of the presentation is not in chronological order. It aims at presenting an approach to a wide range of problems in computer vision and machine learning that is data-driven, local and requires a minimal number of assumptions. The tensor voting framework combines these properties and provides a unified perceptual organization methodology applicable in situations that may seem heterogeneous initially. We show how several problems can be posed as the organization of the inputs into salient perceptual structures, which are inferred via tensor voting. The work presented here extends the original tensor voting framework with the addition of boundary inference capabilities; a novel re-formulation of the framework applicable to high-dimensional spaces and the development of algorithms for computer vision and machine learning problems. We show complete analysis for some problems, while we briefly outline our approach for other applications and provide pointers to relevant sources.
摘要註
This lecture presents research on a general framework for perceptual organization that was conducted mainly at the Institute for Robotics and Intelligent Systems of the University of Southern California. It is not written as a historical recount of the work, since the sequence of the presentation is not in chronological order. It aims at presenting an approach to a wide range of problems in computer vision and machine learning that is data-driven, local and requires a minimal number of assumptions. The tensor voting framework combines these properties and provides a unified perceptual organization methodology applicable in situations that may seem heterogeneous initially. We show how several problems can be posed as the organization of the inputs into salient perceptual structures, which are inferred via tensor voting. The work presented here extends the original tensor voting framework with the addition of boundary inference capabilities; a novel re-formulation of the framework applicable to high-dimensional spaces and the development of algorithms for computer vision and machine learning problems. We show complete analysis for some problems, while we briefly outline our approach for other applications and provide pointers to relevant sources.
內容註
Introduction -- Tensor Voting -- Stereo Vision from a Perceptual Organization Perspective -- Tensor Voting in ND -- Dimensionality Estimation, Manifold Learning and Function Approximation -- Boundary Inference -- Figure Completion -- Conclusions.