作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (12): 202-204. doi: 10.3969/j.issn.1000-3428.2007.12.071

• 人工智能及识别技术 • 上一篇    下一篇

结合高维空间几何计算的图像阴影消除新方法

朱世交1,2,张南华1,2   

  1. (1. 同济大学计算机科学与工程系,上海 200092;2. 同济大学半导体与信息技术研究所,上海 200092)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-06-20 发布日期:2007-06-20

New Method of Image Shadows Elimination Combining High Dimension Geometry Calculation

ZHU Shijiao1,2, ZHANG Nanhua1,2   

  1. (1. Department of Computer Science and Engineering, Tongji University, Shanghai 200092; . Institute of Semiconductors & Information Technology, Tongji University, Shanghai 200092)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-06-20 Published:2007-06-20

摘要: 提出了一种结合高维空间几何计算的图像消影方法,通过一组光滑滤波核与原始图像作用,生成一幅新的特征图像点,将此2个图像映射成为高维空间中的2个点,测算空间中点与特征图像向量的欧式距离,获得到消除阴影后的最终图像。实验表明,即使对于不同种类图像,该方法也可以获得很好的阴影增强效果。

关键词: 高维空间几何计算, 图像消影, 图像增强

Abstract: This paper presents a new method for eliminating shadowed digital image combining high-dimension geometry calculation . In order to calculate a new image based on original one, it gets the new image through the way of convolution original image with a set of smoothing filter kernels, and then calculates the distance in Euclidean space and gets the last image point. Experimental results have shown there are better effects for shadowed image even for different category pictures.

Key words: High-dimension space geometry, Shadows elimination, Image enhancement

中图分类号: