BSCB与块平移法小波域融合的数字视频修复

Digital Video Restoration By Wavelet Fusion of BSCB and Block Translation

提出了一种BSCB(Bertalmio-Sapiro-Caselles-Bellester)与块平移法小波域融合的数字视频修复算法.首先利用BSCB修复当前视频帧的破损部分,之后利用块平移法将后一视频帧中对应位置的完整部分平移到当前帧破损部分.以上两种方法得到两种修复结果,然后在小波域对其按照一定规则融合.通过合理地选择母小波,将待融合视频帧分解为结构部分和细节部分;之后对各分解层分别进行融合处理,低频部分通过加权平均进行处理,高频部分则采用绝对值取大进行处理,最后对融合后的小波视频帧进行小波逆变换,所得重构结果即为融合后的视频帧.实验验证了视频修复算法的有效性.

A digital video restoration algorithm by wavelet fusion of tASCB and block translation is pro- posed in this paper. First of all, the author ases using BSCB model to repair the damaged part of the cur- rent frame, replaces the current frame damaged parts with the next frame-s complete parts by block trans- lation algorithm. And using wavelet weighted fusion to restore the image by the pre-two algorithms. Through perfect re-factoring capability of the wavelet, the mother wavelets are chosen, image can be de- composed into average image and detail image, which are the structure part and detail part of un-fused vid- eo frame. The low frequency part is processed by the weighted average method, while high frequency part has been adopted the absolute value algorithm. Finally, inverse transform of the fused coefficients is imple- mented in order to obtain the final fusion image. Experiments show the feasibility of the algorithm.