首页> 外国专利> Self-optimizing edge detection in blurred, high-noise images

Self-optimizing edge detection in blurred, high-noise images

机译:在模糊高噪声图像中进行自我优化的边缘检测

摘要

An apparatus, program product and method detect region boundaries, or edge, of an arbitrary number of pixels in width in a digital image that has coarse resolution, high noise levels and/or significant blur. A self-optimizing kernel generator detects edges of arbitrary thickness. In addition, combining results of multi-resolution edge detection provides significant noise tolerance, such as a 10 dB improvement over conventional techniques. Moreover, the edge detection preserves the precise location of a blurred edge and quantifies image clarity.
机译:一种设备,程序产品和方法,检测具有粗糙分辨率,高噪声水平和/或明显模糊的数字图像中宽度上任意数量的像素的区域边界或边缘。自优化内核生成器可检测任意厚度的边缘。另外,结合多分辨率边缘检测的结果可提供显着的噪声容限,例如比常规技术提高10 dB。此外,边缘检测可保留模糊边缘的精确位置并量化图像清晰度。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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