基于形态插值的图像重建方法

Images Processing Method Based on Morphological Interpolation

该文提出了一种基于数学形态学的形态插值方法,该方法适用于对于二值图像、灰值图像以及多光谱图像的插值重构,通过形态插值技术将输入图像变换成保持某种特征的插值图像。所提出的方法是对基于测地距离函数和形态中值方法的扩展,以提高插值方法的有效性为目的。该文还从应用的角度对于分割序列图像的插值重建算法进行了研究,所获得的新算法能较好地应用于各种类型图像的插值与形变。

In the paper,image interpolation methods based on the mathematical morphology are proposed.The methods include binary images interpolation,gray images interpolation and multi-spectral images interpolation technique,and allow transforming one input object into another one.The proposed method is an improvement of the geodesic distance function approach and morphological median approach,which increases the method's effectiveness.In addition,a new algorithm for partition sequence interpolation is proposed,it can be successfully applied to metamorphosis for different image.