Learning Probability Models for Surface Appearance and Shape by Minimax Entropy Principle

通过最小最大熵原理学习表面外观和形状的概率模型

• 批准号: 9877127
• 负责人: Song-Chun Zhu
• 金额: $ 36.86万
• 依托单位: Ohio State University Research Foundation -DO NOT USE
• 依托单位国家: 美国
• 项目类别: Continuing grant
• 财政年份: 1999
• 资助国家: 美国
• 起止时间: 1999-08-15 至 2003-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9877127&HistoricalAwards=false
• 关键词: Learning; Probability; Models; Surface; Appearance

Abstract IIS-9877127Zhu, Song-ChunOhio State University$115,872 - 12 mos.Learning Probability Models for Surface Appearance and Shape by Minimax Entropy PrincipleThis is the first year funding of a three year continuing award. The research in this project is aimed at three important problems in visual learning. 1). Studying a mathematical theory for visual learning. 2). Learning realistic probability models for textures, object shapes, clutter, and texton flows, which are essential constructing components of natural scenes. 3). Developing fast algorithms for model inference and model verification. Central to the research is the minimax entropy learning theory, proposed by the PI, the co-PI, and Mumford in 1997. The minimax entropy learning theory is capable of exploring the intrinsic structures (or regularities) underlying the observed imagery and patterns. The outcomes of this learning theory are statistical models of the visual patterns for textures, object shapes, clutter, and texton flows. The learned models can be used in the Bayesian framework as likelihood functions and prior probabilities, which are essential for the success of Bayesian image analysis paradigm in applications such as image segmentation, perceptual organization, and object recognition. The PI and Co-PI have achieved good preliminary results, and together, they form an effective interdisciplinary team to conduct the research.

摘要IIS-9877127朱松春，俄亥俄州立大学$115，872 - 12月。学习概率模型的表面外观和形状的最小最大熵原则这是第一年的资金，为期三年的连续奖励。 本研究针对视觉学习中的三个重要问题。 1）。研究一 视觉学习的数学理论2）的情况。学习纹理，物体形状，杂波和纹理元流的真实概率模型，这些都是自然场景的基本组成部分。3）。开发模型推理和模型验证的快速算法。该研究的核心是极大极小熵学习理论，由PI，co-PI和Mumford于1997年提出。极小极大熵学习理论能够探索所观察到的图像和模式的内在结构（或结构）。这种学习理论的成果是纹理，物体形状，杂乱和纹理元流的视觉模式的统计模型。学习的模型可以在贝叶斯框架中用作似然函数和先验概率，这对于贝叶斯图像分析范式在图像分割，感知组织和对象识别等应用中的成功至关重要。PI和Co-PI已经取得了良好的初步成果，他们共同组成了一个有效的跨学科团队进行研究。