欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出一种新颖的图像分解算法,用于复杂背景下的路面病害图像,可以获得较为清晰的裂纹病害信息。通过对含有局部线性特征的裂纹图像进行形态分析,建立与结构特征相匹配的基底,利用局部Ridgelet函数作为稀疏表示的基底,图像中的结构信息作为一种组成成分被提取出来,同时运用全变差正则化方法对提取的结构信息加以正则化约束,使得提取结果更加精细化。实验结果表明利用该算法提取的裂纹病害信息符合人眼的观测结果。
英文摘要：
A novel image decomposing algorithm is proposed in this paper,which can obtain clear pavement crack information under complicated background.By means of morphological analysis of the image containing local linear features,the basis that matches the structural features can be set up.The structure information in the image can be drawn as one component by using local Ridgelet as the basement of sparse decomposing.Moreover,total-variation regularization scheme can be utilized to regularly restrict the structure information and the results can be drawn more meticulously.Experiment results show that the crack information drawn by the proposed method is in accordance with human visual system.
同期刊论文项目
同项目期刊论文
The spontaneous emission rate of an atom in a two-layer dielectric slab between two parallel mirrors
The recurrence spectra of the Rydberg hydrogen atom interacting with a metallic surface and an elect
位置：