计算机科学与探索 ›› 2017, Vol. 11 ›› Issue (7): 1150-1158.DOI: 10.3778/j.issn.1673-9418.1604052

• 人工智能与模式识别 • 上一篇    下一篇

基于马尔科夫随机场匹配准则的Criminisi修复算法

赵  娜,王慧琴+,吴  萌   

  1. 西安建筑科技大学 信息与控制工程学院,西安 710055
  • 出版日期:2017-07-01 发布日期:2017-07-07

Criminisi Digital Inpainting Algorithm Based on Markov Random Field Matching Criterion

ZHAO Na, WANG Huiqin+, WU Meng   

  1. School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China
  • Online:2017-07-01 Published:2017-07-07

摘要: 传统的基于样本的修复算法在修复数字图像时精度较低,提出了一种基于马尔科夫随机场(Markov random field,MRF)匹配准则的Criminisi数字图像修复算法。该算法以马尔科夫随机场替代欧氏距离匹配准则,在寻找最佳匹配块前首先通过马尔科夫随机场对图像纹理建模,然后计算图像全局能量对待修复像素块进行估值,最后寻找最佳匹配块以达到全局最优。实验结果表明,该算法对数字图像的修复有了很大改善,纹理误匹配率下降,修复精度得到明显提高。

关键词: Criminisi, 马尔科夫随机场(MRF), 匹配准则, 图像修复

Abstract: The accuracy of traditional image exemplar-inpainting algorithm is lower. This paper proposes a new Criminisi digital inpainting algorithm based on Markov random field (MRF) matching criterion. The MRF becomes new matching criterion instead of Euclidean distance. Before searching the best matching patch, the image texture model based on MRF is built. Then the global energy of the image is calculated to estimate the value of inpainting patch. Finally, the best matching patch is searched in order to achieve the global optimum. The experimental results show that the proposed algorithm achieves impressive inpainted results, the texture error matching rate is decreased, and the inpainting accuracy is improved.

Key words: Criminisi, Markov random field (MRF), matching criterion, image inpainting