流状线型结构图像修复算法的研究

Flow-like textures with line-like structures images inpainting by improved tensor diffusion model

针对流状线型结构图像修复问题,提出了一种基于张量扩散的流状结构图像修复算法,模型根据图像局部结构(局部图像结构由结构张量来度量)的纹理走向确定沿纹理方向和垂直纹理方向的扩散来修复断裂特征,并且控制沿纹理方向的扩散强度要大于沿垂直纹理方向的扩散强度,由此才能保证较好的纹理修复。为使计算结果更加准确,采用了非负性离散化和最优化旋转不变性两种数值计算方案。实验结果表明,对于有划痕或较小损坏区域的流状线型结构的纹理图像,该算法都能取得较好的修复结果。

For inpainting of the flow-like textures with line-like structures images,a model based on tensor diffusion is presented.The proposed model is to reconstruct a damaged original image by acting along the texture＇s direction and the vertical texture＇s direction which is determined by the texture＇s trend of the local image structure（This local image structure is measured by the so-called structure tensor）.In order to guarantee better results,the intensity of the diffusion along the texture＇s direction should be much greater than that of the diffusion along the vertical texture＇s direction.The nonnegativity discretization method and optimized rotation invariance method is used to get more accurate results.Experiments results show that this model can get good results for inpainting the flow-like textures with line-like structures images that contain nicks or small broken areas.