基于Hough变换的运动模糊方向鉴别方法

Identification of Motion Blurred Image Direction Based on Hough Transform

曝光的瞬间,由于物体与成像系统产生相对运动造成图像降质而导致图像模糊,这一短暂过程虽可近似地作为匀速直线运动来处理,但是模糊图像中模糊方向未知。若能从模糊图像出发,估计出运动模糊方向,则可通过图像旋转将运动方向旋转到水平轴,这样图像复原问题就可由二维降为一维,大大降低图像复原的难度。为了实现这一目的,提出了一种基于Hough变换的运动模糊方向的估计方法。实验表明,该方法不仅可鉴别出运动模糊方向,而且具有鉴别范围大、鉴别精度高、稳定性好的优点。

During the short expose time, the relative motion between moving objects and camera blurs the image. Although the process can be dealt with as uniform linear motion, the motion blur direction is unknown. It is meritorious to identify the motion blur direction from the blurred images. And then the motion blurred direction can be adjusted to the horizontal axis by image rotation, and the image restoration will become a one - dimension problem, which is much more easy than the two - dimension that it was. In this paper, a novel method is proposed to achieve the aims based on Hough transform. The new way to identify direction of blur image enhances the identification stabilization and work out higher identification precision.