一种高效的分层自动鉴别模糊长度方法

An Efficient Method to Automatically Identifying the Blurred Length by Classifying Layer

提出了基于图像微分和自相关函数的分层自动鉴别模糊长度方法。通过对水平运动模糊图像或任意角度旋转至水平方向的运动模糊图像先按大小分为不同的层次,再对各层图像计算水平方向的微分,计算水平方向的自相关函数值,得到的结果把各列相加,绘制相应的鉴别曲线,从鉴别曲线中寻找一对最小值的距离用于计算该层次图像的模糊长度估计值,最后选取一组相近的长度估计值求其平均值作为整幅图像的模糊长度。实验表明,自动鉴别方法执行效率更好,精度更高。

This paper proposes a method of identifying the blurred length in the spatial domain on the basis of image differential coefficient and autocorrelation function.The paper classifies the motion-blurred images or motion blurred images rotating from any angles to the horizontal level into different levels according to their sizes,calculates the horizontal differential coefficients of each layer image and the autocorrelation function of horizontal level,adds up the sum of each column,draws the relevant differential curve,finds the minimum distance used to calculate the blurred length,estimates the image at this layer from the differential curves.Finally,the author selects a group of similar length estimated for the average of blurred length of the whole image.The result of the experiment shows that automatic identification proposed in this paper functions more efficiently and more accurately.