欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2006, Vol. 23 ›› Issue (5): 665-670.DOI: 10.7523/j.issn.2095-6134.2006.5.016

• 论文 • 上一篇    下一篇

基于梯度场整体变分模型的无缝图像处理方法

葛仕明; 程义民; 曾丹; 李杰   

  1. 中国科学技术大学电子科学与技术系, 合肥 230026
  • 收稿日期:1900-01-01 修回日期:1900-01-01 发布日期:2006-09-15

Seamless Image Processing Based on Gradient Field Total Variation Model

Ge Shi-ming; Cheng Yi-min; Zeng Dan; Li Jie   

  1. Dep. of Electronic Science & Technology, University of Science & Technology of China, Hefei 230026, China
  • Received:1900-01-01 Revised:1900-01-01 Published:2006-09-15

摘要: 提出了一种在梯度域中进行无缝图像处理的方法。在一般的整体变分模型中引入待处理区域的梯度场,得到一个扩展的整体变分模型,称为梯度场整体变分(gradient field total variation, GFTV)模型。无缝处理通过最小化模型函数来实现。基于GFTV模型的方法可应用于以下无缝图像处理:在图像中无缝地插入新的目标;无缝地修改图像中的某个区域的纹理、光照等外观;图像的无缝拼接等。

关键词: 无缝图像处理, 整体变分模型, 梯度场, 图像拼接

Abstract: This paper presents a novel framework for seamless image processing in gradient domain. A gradient field of image region to be processed is introduced into general total variation(TV) model, which gives an extended version of TV model called gradient field total variation (GFTV)model. Seamless processing is performed by minimizing the model function. Through our framework based on GFTV model, a variety of applications for seamless image processing are introduced, mainly including seamless importation of source image regions into destination image, modifying the appearance, e.g. texture, illumination, of the image seamlessly within a selected region, and image seamless stitching.

Key words: seamless image processing, total variation (TV) model, gradient field, image stitching

中图分类号: