计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (7): 194-196.

• 图形、图像、模式识别 • 上一篇    下一篇

一种改进的整体变分图像修复方法

刘庚龙1,檀结庆1,2   

  1. 1.合肥工业大学 计算机与信息学院,合肥 230009
    2.合肥工业大学 应用数学研究所,合肥 230009
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2012-03-01 发布日期:2012-03-01

Improved method of total variation image inpainting

LIU Genglong1, TAN Jieqing1,2   

  1. 1.College of Computer & Information, Hefei University of Technology, Hefei 230009, China
    2.Institute of Applied Mathematics, Hefei University of Technology, Hefei 230009, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2012-03-01 Published:2012-03-01

摘要: 提出了一种基于整体变分模型的图像修复方法,该方法通过计算像素点的梯度信息来构造一个扩散函数,再进行加权处理,达到了对原模型的改进。实验表明,该方法修复有较大破损区域的图像效果比较好,边缘过渡更自然。

关键词: 图像修复, 整体变分, 梯度, 加权, 扩散函数

Abstract: This paper presents an image restoration algorithm based on total variation model, this method improves the original model through constructing a spread function by calculating the gradients of the pixel, and then carrying out the weighted approach. Experiments show that this algorithm works better in the restoration of damaged images which have rich texture, and has more natural boundary transit.

Key words: image inpainting, total variation, gradient, weighted, spread function