In computer vision, superpixel segmentation has been widely used as a very important preprocessing to reduce the number of image primitives for subsequent image processing tasks. To improve the segmentation accuracy and the robustness to noise, a hierarchical multi-level segmentation framework is developed in this paper. First, original image is initially segmented by a local information based simple liner iterative clustering (LI-SLIC) method. Then, the initial generated superpixels are further segmented hierarchically by LI-SLIC to ensure that all pixels contained within each superpixel belong to a same object. Finally, to eliminate over-segmentation and reduce the number of superpixels, adjacent superpixels belonging to a same object are merged based on the probability distribution similarity. The proposed method does not require setting the seeds or number of the superpixels to be generated in advance, which can segment image into an appropriate number of superpixels without under- or over- segmentation automatically according to its content. Experiments are conducted on two public datasets Berkeley and 3Dircadb, and the results demonstrate that our method is more effective and accurate than many existing superpixel methods and shows a great advantage in dealing with images corrupted by various noises.

在计算机视觉中，超像素分割已被广泛用作一种非常重要的预处理，以减少用于后续图像处理任务的图像基元的数量。为了提高分割的准确性和鲁棒性，本文提出了一种分层的多层分割框架。首先，原始图像首先通过基于局部信息的简单线性迭代聚类（LI-SLIC）方法进行分割。然后，通过LI-SLIC对初始生成的超像素进行进一步分层，以确保每个超像素中包含的所有像素都属于同一对象。最后，为了消除过度分割并减少超像素的数量，基于概率分布相似度将属于同一对象的相邻超像素合并。所提出的方法不需要预先设置要产生的超像素的种子或数量，这可以将图像分割成适当数量的超像素，而不会根据其内容自动进行过分或过分分割。在两个公共数据集Berkeley和3Dircadb上进行了实验，结果表明我们的方法比许多现有的超像素方法更有效和准确，并且在处理受各种噪声破坏的图像方面显示出很大的优势。