摘要
提出一种基于分解的图像修复算法,该算法对敦煌壁画的数字图像进行修复。选择用Lαβ色彩空间进行通道分解实现彩色图像的修复,并利用整体变分降噪模型进行图像分解,该分解算法不需要进行Banach空间范数的计算,不仅降低模型的数值计算复杂度,还可以降低敦煌壁画中的噪声对修复结果的影响。实验证明:该算法很好地解决壁画中的划痕和脱落等现象的破损,修复效果较好。
An algorithm for image in-painting based on decomposition was proposed to in-paint the digital images of Dunhuang murals.The color image in-painting was achieved by using the Lαβ color space for the access decomposition and by using the total variation（TV）noise model for image decomposition.The decomposition algorithm did not require the calculation of Banach space norm.This method could not only reduce the complexity of the numerical calculation of the model,but also reduce the affection that noise made on the results of repair in Dunhuang murals.The experiments showed that this algorithm could well in-paint the shedding and scratch of the damaged Dunhuang murals.
出处
《山东大学学报（工学版）》
CAS
北大核心
2010年第2期24-27,33,共5页
Journal of Shandong University（Engineering Science）
基金
国家自然科学基金资助项目(60675059)
甘肃省科技攻关资助项目(2GS057-A52-005-02)
关键词
图像修复
图像分解
结构
纹理
Lαβ色彩空间
image in-painting
image decomposition
structure
texture
Lαβ color space
