基于Wasserstein距离的局部能量分割模型

 提出了一种基于Wasserstein距离和图像局部区域直方图信息的非参数活动轮廓分割模型.用该距离对图像中不同区域的直方图进行比较,提高了相似性衡量的准确性;引入高斯内核函数来获取图像局部区域直方图信息,并将信息嵌入模型指导轮廓演化,以克服由于亮度不均造成的图像分割困难;通过水平集规范项提高计算精度并避免水平集演化的重新初始化.实验结果表明,本模型能够对亮度不均的无序特征图像进行有效准确的分割.

Wasserstein Distance Based Local Energy Model of Segmentation

A nonparametric Wasserstein distance-based active contour model that is able to utilize image histogram information in local region is presented. To quantify the similarity between two regions, we proposed to compare their respective histograms using the Wasserstein distance; Due to a Gaussian kernel introduced, intensity information in local regions is extracted and embedded in model to guide the motion to overcome the difficulties in image segmentation caused by intensity inhomogeneities. In addition, the regularity of the level set function is intrinsically preserved by the level set regularization term to ensure accurate computation and avoids expensive reinitialization of the evolving level set function. Experiment results prove that our model segments texture images with intensity inhomogeneity effectively.