基于梯度和流形的超像素分割算法

SUPERPIXEL SEGMENTATION BASED ON GRADIENT AND MANIFOLD

当今许多图像处理任务常用超像素作为降维手段和边缘优化的依据。针对现有方法分割数量过于依赖经验和存在离散点的问题,提出一种基于梯度和流形距离的超像素数量的分割方法,自适应估算图像适合的超像素数量,令细节的分割更为精准同时减少背景区域的过分割。以BSDS500数据集进行实验,该方法在各项指标上有较好表现,尤其解决了离散点问题,在紧致度上得到巨大提升。

In today s image processing tasks,the super pixel is often used as a method of dimensionality reduction for image as well as the basis of edge optimization.A super-pixel segmentation method based on gradient and manifold distance is proposed to solve the problem of experience-dependent segment number and discrete point of existing methods.It estimated the suitable number of superpixels for images adaptively,making segmentation for details more accurate and reducing over-segmentation for background.Experiments were conducted on BSDS500 dataset.We achieved good performance in various indicators.Escpecially,the elimination of discrete points leads to the compact with huge improvement.