摘要
图像修补技术一直被广泛地用于重建旧照片和移除一些在图片背景中不想要的物体。提出了一种新的图像修补方法,该方法基于样本的图像修补思想。我们的方法通过合理的信心度和数据条件的计算方法改进了图像修补的有效性和增强图像中线性结构扩散。因此,用本方法进行图像修补时,能有效地避免其他算法共同存在的"垃圾物"的生成问题。实验结果表明,与其他类似方法相比,本方法能够得到更令人满意的视觉效果。
Image inpainting technique has been widely used for reconstructing damaged old photographs and removing unwanted objects from images. A new image inpainting method was proposed based on exemplar-based image inpainting idea. The method improves effectiveness and the linear structure propagation by rational confidence and data computing method. Therefore, the method can effectively avoid the ＂garbage＂ produced during the process of inpainting, which is a common problem in other methods. With the method, one can obtain more pleasurable vision results than those obtained by other similar methods.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2008年第10期2606-2608,2613,共4页
Journal of System Simulation
基金
国家自然科学基金(10171026、60473114)
安徽省自然科学基金(070416273X)
安徽省教育厅科技创新团队基金(2005TD03)
关键词
图像修补
纹理合成
目标去除
优先权
等照度
image inpainting
texture synthesis
object remove
priority
isolux
