电影胶片由于长期存放和多次播放，因此存在着灰尘、污垢、霉斑、图像抖动、划痕、闪烁、噪声、变色、模糊等问题，其中垂直划痕是比较常见的一种损伤。为了消除这种损伤，通过垂直划痕小波特性的分析，提出了一种垂直划痕检测和去除的算法。该算法基于二进离散小波变换，首先将图片分解成为概貌和细节分量；然后通过对水平和垂直细节分量的分析，结合形态学的处理手段得到划痕位置，并比较了在空间域和小波域重建划痕区域内丢失的信息的各种方法，最终选择在小波域进行划痕修复。结果显示，采用该新方法进行划痕的检测和去除，不仅简单而且有效。

Movie films are often damaged by aging and multiple playing, which may cause some artifacts on the fihns, such as dust spots, dirt, blotches, film unsteadiness, line scratches, flicker, noises, color variations and blurs. Vertical scratch is one of the artifacts we can often see. To eliminate this artifact, we analyze the character of the line scratch and give a method for detection and removal of it. The proposed algorithm is based on the discrete binary wavelet decomposition, This transformation splits an image into approximation and detail coefficients. The locations of the scratches are gained through analyzing the horizontal and vertical components and using morphologic methods. We compare various algorithms that reconstruct the missing data in the region of the scratch, and choose to restore the scratch regions in the wavelet domain. The results show that the algorithm of scratch detection and removal in this paper is simple and effective.