摘要
在使用基于样本的纹理合成技术的图像修复算法中,搜索纹理的匹配块时,利用纹理的方向特性,可以将搜索过程约束到沿着纹理的方向进行。在CriminisiA的算法基础上,加入了确定纹理方向过程,优化了纹理块的优先权和大小的计算方法。实验结果表明,该方法在处理强方向性的纹理图像的修复时有很好的效果,明显地提高了计算效率。
The method was introduced to compute the main direction of the texture and complete the image by limiting the search to one direction to carry out image completion based on Exemplar-Based image completion. The method computed the main direction of the texture and improved the template window＇s priority and size based on Criminisi A＇s algorithm. A number of examples were given to demonstrate the effectiveness of the proposed algorithm on dealing with the image with strong orientation of texture distribution and raising efficiency obviously.
出处
《计算机应用》
CSCD
北大核心
2008年第9期2315-2317,共3页
journal of Computer Applications
关键词
图像修复
纹理方向
纹理合成
目标去除
image inpainting
texture orientation
texture synthesis
object removal
