• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Imaging Science and Technology >Fast Multispectral2Gray
【24h】

Fast Multispectral2Gray

机译：快速多光谱灰色

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

A standard approach in generating a grayscale equivalent to an input multispectral image involves calculating the so-Galled structure tensor at each image pixel. Defining contrast as associated with the maximum-change direction of this matrix, the gray gradient is identified with the first eigenvector direction, with gradient strength given by the square root of its eigenvalue. However, aside from the inherent complexity of such an approach, each pixel's gradient still possesses a sign ambiguity since an eigenvector is given only up to a sign. This is ostensibly resolved by looking at how one of the color channels behaves, or how the luminance changes, or how overall integrability is affected by each sign choice. Instead, the authors would like to circumvent the sign problem in the first place and also avoid calculating the costly eigenvector decomposition. The authors suggest replacing the eigenvector approach by generating a grayscale gradient equal to the maximum gradient among the color or multispectral channels' gradients in each pixel. In order not to neglect the tensor approach, the authors consider the relationship between the complex and the simple approaches. The authors also note that, at each pixel, the authors have both forward-facing and backward-facing derivatives that are different. In a novel approach, the authors consider a tensor formed from both. Then, over a standard training set, the authors ask for an optimum set of weights for all the maximum gradients such that the simple maxima scheme generates a grayscale structure tensor to best match the original multispectral one. If the authors use only forward-facing derivatives, a fast Fourier-based solution is possible. But instead, the authors find that a simple scheme that equally weights maxima in the forward-facing and backward-facing directions produces superlative results if a reset step is included in a spatial domain solution. Grayscale results are shown to be excellent, and the algorithm is very fast.
机译：生成等效于输入多光谱图像的灰度的标准方法涉及在每个图像像素处计算如此高的结构张量。将对比度定义为与此矩阵的最大变化方向相关联，即可通过第一个特征向量方向识别灰色渐变，渐变强度由其特征值的平方根给出。但是，除了这种方法固有的复杂性之外，每个像素的梯度仍然具有符号歧义性，因为特征向量仅给出一个符号。通过观察颜色通道之一的行为，亮度如何变化或每个符号选择如何影响整体可集成性，表面上可以解决此问题。相反，作者希望首先避开符号问题，并且还避免计算代价高昂的特征向量分解。作者建议通过生成等于每个像素的颜色或多光谱通道的梯度中的最大梯度的灰度梯度来代替特征向量方法。为了不忽略张量方法，作者考虑了复杂方法和简单方法之间的关系。作者还注意到，在每个像素处，作者都具有不同的前向和后向导数。在一种新颖的方法中，作者考虑了由两者形成的张量。然后，在标准训练集上，作者要求为所有最大梯度设置最佳的权重集，以使简单的最大值方案生成灰度结构张量，以最佳地匹配原始的多光谱张量。如果作者仅使用前向导数，则可以使用基于快速傅里叶的解决方案。但是，相反，作者发现，如果在空间域解决方案中包含重置步骤，则在向前和向后方向均等加权最大值的简单方案将产生最高级的结果。灰度结果显示非常好，算法非常快。

著录项

  • 来源
    《Journal of Imaging Science and Technology》 |2009年第6期|060401.1-060401.10|共10页
  • 作者

    Ali Alsam; Mark S. Drew;

  • 作者单位

    Faculty of Informatics and e-Learning (AITeL), Sor-Trondelag University College, Trondheim, 7012 Norway;

    School of Computing Science, Simon Fraser University, Vancouver, British Columbia, Canada V5A 1S6;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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