计算机与现代化 ›› 2020, Vol. 0 ›› Issue (07): 117-120.doi: 10.3969/j.issn.1006-2475.2020.07.022

• 图像处理 • 上一篇    下一篇

基于广义全变分正则项的图像填补技术

  

  1. (闽南师范大学物理与信息工程学院电子工程系,福建漳州363000)
  • 出版日期:2020-07-06 发布日期:2020-07-15
  • 作者简介:陈颖频(1986-),男,福建漳州人,讲师,博士,研究方向:压缩感知,时频分析技术,凸优化理论,目标跟踪技术,E-mail: 110500617@163.com; 柯素玲(1997-),女,福建泉州人,本科生,研究方向:图像处理; 黄慧滢(1999-),女,福建泉州人,本科生,研究方向:图像处理; 吴日盛(1998-),男,湖北黄冈人,本科生,研究方向:图像处理; 王灵芝(1981-),女,福建南平人,副教授,硕士,研究方向:嵌入式系统设计,图像处理。
  • 基金资助:
    福建省重大教学改革基金资助项目(FBJG20180015); 闽南师范大学校级教改基金资助项目(JG201918,JG201919); 闽南师范大学校长基金资助项目(KJ19019)

Image Inpainting Technology Based on Total Generalized Variation Regularization

  1. (Department of Electronic Engineering, School of Physics and Information Engineering of 
    Minnan Normal University, Zhangzhou 363000, China)
  • Online:2020-07-06 Published:2020-07-15

摘要: 图像填补是当前数字图像处理和计算机图像学中的一个热点问题。为更好地填补图像,基于广义全变分提出一种新的图像填补模型。在数值计算上,采用一阶原始对偶算法对所提新模型进行求解,然后采用结构相似性、峰值信噪比进行评价。实验结果表明,提出算法能获得较好的图像恢复效果。

关键词: 广义全变分, 全变分, 一阶原始对偶, 图像填补

Abstract: Image inpainting is a hot spot in digital image processing and computer graphics. To better recover the image, a new image inpainting model based on total generalized variation is proposed. Then, the first order primal dual method is employed to solve the proposed model. The experiments are carried out to verify the presented scheme based on the value of similarity index and the peak signal to noise ratio. The experimental results show that the proposed scheme is capable of achieving good image recovery quality.

Key words: total generalized variation, total variation, first order primal dual method, image inpainting

中图分类号: