计算机应用 ›› 2013, Vol. 33 ›› Issue (08): 2317-2319.

• 多媒体处理技术 • 上一篇    下一篇

基于梯度域的保纹理图像阴影去除算法

黄微,傅利琴,王琛   

  1. 上海大学 通信与信息工程学院,上海 200072
  • 收稿日期:2013-03-01 修回日期:2013-04-19 出版日期:2013-08-01 发布日期:2013-09-11
  • 通讯作者: 黄微
  • 作者简介:黄微(1980-),女,湖南汉寿人,讲师,博士,主要研究方向:图像信息恢复与重建;
    傅利琴(1987-),女,浙江绍兴人,硕士,主要研究方向:自然图像阴影恢复;
    王琛(1988-),男,安徽淮南人,硕士研究生,主要研究方向:图像去噪、图像重建。
  • 基金资助:
    国家青年自然科学基金资助项目

Texture-preserving shadow removal algorithm based on gradient domain

HUANG Wei,FU Liqin,WANG Chen   

  1. School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China
  • Received:2013-03-01 Revised:2013-04-19 Online:2013-09-11 Published:2013-08-01
  • Contact: HUANG Wei

摘要: 针对当前自然图像阴影去除算法需要多次人工交互、阴影去除结果纹理信息丢失等问题,提出了基于梯度域的图像保纹理阴影去除算法。该方法只需确定出阴影的大概边界,然后在梯度域中,分别对阴影内部和阴影边界的梯度进行最优化修正,得到无阴影的梯度图像,最后利用泊松方程,恢复出无阴影图像。利用多幅图像的实验结果证明,该算法操作简单,不需要多次人机交互,且阴影区域内纹理细节得到了较好的恢复。

关键词: 阴影去除, 阴影检测, 梯度域, 泊松方程, 纹理特征

Abstract: Accurate shadow boundary detecting and texture-preserving are two critical difficulties in shadow removal. To solve these problems, a new shadow removal method based on gradient field was proposed. Firstly, shadow boundary was detected approximately. Then, the gradients in internal shadow region and shadow boundary were modified respectively to obtain the non-shadowed gradient field. Based on the gradient field, the information in shadow regions was recovered with Poisson equation. The experimental results with several images indicate that the method can remove shadow from images easily while preserving the textures in the shadow regions, and it is not sensitive to the accuracy of shadow boundary.

Key words: shadow removal, shadow detection, gradient domain, Poisson equation, texture feature

中图分类号: