Abstract: As the quality of the repaired image is significantly influenced by the filling order of the boundary pixels, this paper tries to compute priority to improve the exemplar-based algorithm by means of D-S evidence theory, according to analyzing the pixel’s surrounding image features and taking into account the proportion of the image texture features and structural characteristics. Experimental results of the algorithm is given and proved to be effective in increasing the repaired image’s vision quality.

Key words: image inpainting, priority computation, D-S evidence theory

摘要： 图像的修复质量容易受到待修复区域边界上修复顺序的影响。针对该问题，提出一种基于D-S证据理论的图像修复算法。通过分析待修复区域像素点所在模块周围的图像特征，考虑图像修复优先级计算中纹理特征和结构特征各自所占的比重问题，采用D-S证据理论改进修复算法的优先级计算。实验结果表明，该算法能有效提高图像的修复效果。

关键词: 图像修复, 优先级计算, D-S证据理论

CLC Number: 

• TP751