Superpixels: An evaluation of the state-of-the-art

Abstract

Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003 [1]. By today, publicly available superpixel algorithms have turned into standard tools in low-level vision. As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison. Until now, the rapidly growing number of algorithms as well as varying experimental setups hindered the development of a unifying benchmark. We present a comprehensive evaluation of 28 state-of-the-art superpixel algorithms utilizing a benchmark focussing on fair comparison and designed to provide new insights relevant for applications. To this end, we explicitly discuss parameter optimization and the importance of strictly enforcing connectivity. Furthermore, by extending well-known metrics, we are able to summarize algorithm performance independent of the number of generated superpixels, thereby overcoming a major limitation of available benchmarks. Furthermore, we discuss runtime, robustness against noise, blur and affine transformations, implementation details as well as aspects of visual quality. Finally, we present an overall ranking of superpixel algorithms which redefines the stateof-the-art and enables researchers to easily select appropriate algorithms and the corresponding implementations which themselves are made publicly available as part of our benchmark at davidstutz.de/projects/superpixel-benchmark/.

3D Microstructure Reconstruction of Al-La Microstructure using Diffraction Contrast Tomography and Lifted Multicut

“…To avoid the heavy computational cost, this paper constructs the lifted graph based on the super-pixel algorithm. As suggested by Stutz et al [15] and Wang et al [16], the super-pixel algorithms over-segments the image meshes into much smaller graphs, which greatly reduces the complexity of the following segmentation procedure. As images captured from DCT are always of high resolution, super-pixel algorithms improves the feasibility of the multicut problem.…”

Slic Superpixels for Object Delineation From Uav Data

“…Superpixels can be understood as a form of image segmentation, that oversegment the image in a short computing time. Comparisons to similar approaches that can be found in (Achanta et al, 2012;Csillik, 2016;Neubert and Protzel, 2012;Schick et al, 2012;Stutz, 2015;Stutz et al, 2017) have demonstrated their advantages: The outlines of superpixels have shown to adhere well to natural image boundaries, as most structures in the image are conserved (Neubert and Protzel, 2012;Ren and Malik, 2003). Furthermore, they allow to reduce the susceptibility to noise and outliers as well as to capture redundancy in images.…”

“…State-of-the-art superpixel approaches have been compared in (Achanta et al, 2012;Csillik, 2016;Neubert and Protzel, 2012;Schick et al, 2012;Stutz, 2015;Stutz et al, 2017) considering speed, memory efficiency, compactness of outlines, their ability to adhere to image boundaries and their impact on segmentation performance. Boundary adherence is often measured via boundary recall, indicating how many true edges are missed, and via undersegmentation, indicating to what extent superpixels exceed outlines of the reference data (Achanta et al, 2012;Neubert and Protzel, 2012).…”

“…Boundary adherence is often measured via boundary recall, indicating how many true edges are missed, and via undersegmentation, indicating to what extent superpixels exceed outlines of the reference data (Achanta et al, 2012;Neubert and Protzel, 2012). The SLIC superpixel approach, belonging to the group of gradient-ascent-based approaches, appears as the best overall performer: the algorithm is low in processing time and produces compact and nearly uniform superpixels that are positively evaluated in terms of boundary recall and undersegmentation error (Achanta et al, 2012;Csillik, 2016;Neubert and Protzel, 2012;Schick et al, 2012;Stutz, 2015;Stutz et al, 2017).…”

CoralSeg: Learning coral segmentation from sparse annotations

“…Before the surge of deep learning approaches, several algorithms based on superpixel segmentation techniques (Stutz, Hermans, & Leibe, ) were used for this task. These approaches cluster image pixels into several groups of similar and connected pixels (i.e., superpixels).…”