• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Computational imaging XI >A unifying retinex model based on non-local differential operators
【24h】

A unifying retinex model based on non-local differential operators

机译：基于非局部微分算子的统一retinex模型

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we present a unifying framework for retinex that is able to reproduce many of the existing retinex implementations within a single model. The fundamental assumption, as shared with many retinex models, is that the observed image is a multiplication between the illumination and the true underlying reflectance of the object. Starting from Morel's 2010 PDE model for retinex, where illumination is supposed to vary smoothly and where the reflectance is thus recovered from a hard-thresholded Laplacian of the observed image in a Poisson equation, we define our retinex model in similar but more general two steps. First, look for a filtered gradient that is the solution of an optimization problem consisting of two terms: The first term is a sparsity prior of the reflectance, such as the TV or H1 norm, while the second term is a quadratic fidelity prior of the reflectance gradient with respect to the observed image gradients. In a second step, since this filtered gradient almost certainly is not a consistent image gradient, we then look for a reflectance whose actual gradient comes close. Beyond unifying existing models, we are able to derive entirely novel retinex formulations by using more interesting non-local versions for the sparsity and fidelity prior. Hence we define within a single framework new retinex instances particularly suited for texture-preserving shadow removal, cartoon-texture decomposition, color and hyperspectral image enhancement. Retinex; non-local operators; reflectance; illumination normalization; contrast enhancement; dynamic
机译：在本文中，我们提出了一个retinex的统一框架，该框架能够在单个模型中重现许多现有的retinex实现。与许多retinex模型共享的基本假设是，观察到的图像是对象的照明与真实的基础反射率之间的乘积。从Morel的retinex PDE 2010模型开始，在该模型中照明应该平稳地变化，因此可以从泊松方程中观察到的图像的硬阈值拉普拉斯算子恢复反射率，我们以相似但更通用的两个步骤定义了retinex模型。首先，寻找经过过滤的梯度，这是由两个项组成的优化问题的解决方案：第一个项是反射率之前的稀疏度，例如TV或H1范数，而第二个项是反射率之前的二次保真度。反射率梯度相对于观察到的图像梯度。在第二步中，由于此过滤后的梯度几乎可以肯定不是一致的图像梯度，因此我们寻找其实际梯度接近的反射率。除了统一现有模型外，我们还可以通过使用更有趣的非本地版本来简化和保真度，从而得出全新的retinex公式。因此，我们在一个框架内定义了新的retinex实例，这些实例特别适合于保留纹理的阴影去除，卡通纹理分解，颜色和高光谱图像增强。 Retinex;非本地运营商；反射率照度归一化对比增强；动态

著录项

  • 来源
    《Computational imaging XI》|2013年|865702.1-865702.16|共16页
  • 会议地点 Burlingame CA(US)
  • 作者

    Dominique Zosso; Giang Tran; Stanley Osher;

  • 作者单位

    Department of Mathematics, University of California, Los Angeles (UCLA) 520 Portola Plaza, Box 951555, Los Angeles, CA 90095-1555, U.S.A;

    Department of Mathematics, University of California, Los Angeles (UCLA) 520 Portola Plaza, Box 951555, Los Angeles, CA 90095-1555, U.S.A;

    Department of Mathematics, University of California, Los Angeles (UCLA) 520 Portola Plaza, Box 951555, Los Angeles, CA 90095-1555, U.S.A.;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    range compression; shadow detection; shadow removal; cartoon-texture decomposition;

    机译：范围压缩；阴影检测；去除阴影；卡通纹理分解;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号