Superpixels are perceptually meaningful atomic regions that can effectively capture image features. Among various methods for computing uniform superpixels, simple linear iterative clustering (SLIC) is popular due to its simplicity and high performance. In this paper, we extend SLIC to compute content-sensitive superpixels, i.e., small superpixels in content-dense regions with high intensity or colour variation and large superpixels in content-sparse regions. Rather than using the conventional SLIC method that clusters pixels in $\mathbb {R}^5$ , we map the input image $I$ to a 2-dimensional manifold $\mathcal {M}\subset \mathbb {R}^5$, whose area elements are a good measure of the content density in $I$. We propose a simple method, called intrinsic manifold SLIC (IMSLIC), for computing a geodesic centroidal Voronoi tessellation (GCVT)—a uniform tessellation—on $\mathcal {M}$ , which induces the content-sensitive superpixels in $I$. In contrast to the existing algorithms, IMSLIC characterizes the content sensitivity by measuring areas of Voronoi cells on $\mathcal {M}$ . Using a simple and fast approximation to a closed-form solution, the method can compute the GCVT at a very low cost and guarantees that all Voronoi cells are simply connected. We thoroughly evaluate IMSLIC and compare it with eleven representative methods on the BSDS500 dataset and seven representative methods on the NYUV2 dataset. Computational results show that IMSLIC outperforms existing methods in terms of commonly used quality measures pertaining to superpixels such as compactness, adherence to boundaries, and achievable segmentation accuracy. We also evaluate IMSLIC and seven representative methods in an image contour closure application, and the results on two datasets, WHD and WSD, show that IMSLIC achieves the best foreground segmentation performance.

中文翻译：

---

本征流形SLIC：一种简单高效的计算内容敏感型超像素的方法

超像素是感知上有意义的原子区域，可以有效地捕获图像特征。在各种计算均匀超像素的方法中，简单线性迭代聚类（SLIC）由于其简单性和高性能而广受欢迎。在本文中，我们将SLIC扩展为计算内容敏感的超像素，即，具有高强度或颜色变化的内容密集区域中的小超像素，而内容稀疏区域中的大型超像素。而不是使用传统的SLIC方法对像素进行聚类 $ \ mathbb {R} ^ 5 $ ，我们映射输入图像 $ I $ 到二维流形 $ \ mathcal {M} \ subset \ mathbb {R} ^ 5 $，其面积元素很好地衡量了 $ I $。我们提出了一种简单的方法，称为本征流形SLIC （IMSLIC），用于计算测地线质心Voronoi细分（GCVT）（统一的细分） $ \数学{M} $ ，这会导致对内容敏感的超像素 $ I $。与现有算法相比，IMSLIC通过测量Voronoi细胞在区域上的面积来表征内容敏感性 $ \数学{M} $ 。使用简单，快速的近似于封闭形式的解决方案，该方法可以以非常低的成本计算GCVT，并确保所有Voronoi单元都可以简单连接。我们对IMSLIC进行了全面评估，并将其与BSDS500数据集上的11种代表性方法和NYUV2数据集上的7种代表性方法进行了比较。计算结果表明，IMSLIC在涉及超像素的常用质量度量（例如紧凑性，对边界的遵守以及可实现的分割精度）方面优于现有方法。我们还评估了图像轮廓闭合应用程序中的IMSLIC和七种代表性方法，并且在两个数据集WHD和WSD上的结果表明，IMSLIC实现了最佳的前景分割性能。