• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SIBGRAPI Conference on Graphics, Patterns and Images >Multi-scale Morphological Image Simplification Based on Extrema Relationships: Improvements and Applications
【24h】

Multi-scale Morphological Image Simplification Based on Extrema Relationships: Improvements and Applications

机译：基于极值关系的多尺度形态图像简化：改进与应用

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Image simplification has been proved useful in several image processing applications as an additional step for more complex tasks, such as segmentation and feature extraction. In this work, we explore a graph-based simplification method that guarantees a well-behaved suppression of the image extrema (maxima/minima) by taking into account both information of distance and contrast, as well as some interesting aspects of the scale-space theory. By highlighting some new properties of the method, we define a local update of the graph which implies in an interesting bypass in the whole algorithm structure which, originally, is very time-consuming. Finally, we illustrate how to combine this simplification process with well-known morphological tools to approach problems related mainly with multi-scale image segmentation and homogenization.
机译：事实证明，图像简化在多种图像处理应用中很有用，可作为更复杂任务（如分割和特征提取）的附加步骤。在这项工作中，我们探索一种基于图的简化方法，该方法通过考虑距离和对比度的信息以及比例尺空间的一些有趣方面，确保对图像极值（最大值/最小值）进行良好的抑制。理论。通过突出显示该方法的一些新属性，我们定义了图形的局部更新，这意味着在整个算法结构中进行了有趣的绕过，这原本是非常耗时的。最后，我们说明如何将这种简化过程与众所周知的形态学工具结合起来，以解决主要与多尺度图像分割和均质化有关的问题。

著录项

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