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 ›› 2009, Vol. 35 ›› Issue (6): 234-236. doi: 10.3969/j.issn.1000-3428.2009.06.082

• 图形图像处理 • 上一篇    下一篇

一种新的基于偏微分方程的图像修复

廉晓丽1,徐中宇1,冯丽丽1,晁玉忠2   

  1. (1. 长春工业大学计算机科学与工程学院,长春 130012;2. 武汉理工大学计算机科学与技术学院,武汉 430063)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-03-20 发布日期:2009-03-20

Novel Image Inpainting Based on Partial Differential Equation

LIAN Xiao-li1, XU Zhong-yu1, FENG Li-li1, CHAO Yu-zhong2   

  1. (1. College of Computer Science & Engineering, Changchun University of Technology, Changchun 130012;2. College of Computer Science & Technology, Wuhan University of Technology, Wuhan 430063)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-03-20 Published:2009-03-20

摘要: 图像的修复是图像处理中一个重要的部分,主要是利用一定的方法针对产生划痕和有缺损的图像进行修复,或者从图像中去除指定的物体和文字,以达到特定的目的。该文比较了CDD图像修复模型和快速图像修复模型的性能。它们都满足“连接整体性准则”,对于具有较大破损区域及细小边缘的图像具有良好的修复能力。但是前者修复速度较慢,而后者可以克服CDD修复速度较慢的缺点。实验结果表明,该模型在保证与CDD模型相近修复质量的情况下可以大幅度地提高修复速度。

关键词: 图像修复, 偏微分方程, TV模型, CDD模型, 连接整体性准则

Abstract: Image inpainting is an important part of image processing. It is mainly used to restore the damaged image with some algorithms to attain to special goals, through the restoration of damaged painting with cracks and scratches to the removal or replacement of objects or word. This paper puts emphasis on comparing CDD model with fast inpainting model based on the Curvature Driven Diffusions(CDD). They all realize the connectivity and holistic principle, and have good ability for inpainting the large domain and minute edges, but the former inpainting speed is quite slow, the latter can overcome the shortcoming of slow speed. Experiment demonstrates this fast inpainting model can greatly advance the speed in inpainting, provided with the same quality of QCDD model.

Key words: image inpainting, Partial Differential Equation(PDE), Total Variation(TV) model, Curvature-Driven Diffusions(CDD) model, connectivity and holistic principle

中图分类号: