SymmSLIC: Symmetry Aware Superpixel Segmentation and its Applications
This work addresses a domain-specific problem in image processing and computer vision for applications like symmetry detection and object segmentation, but it is incremental as it builds on existing superpixel methods by adding symmetry awareness.
The authors tackled the problem of superpixel segmentation not preserving reflection symmetry in images, which leads to inconsistent superpixel shapes across symmetry axes, and proposed SymmSLIC, an algorithm that propagates pixel-level symmetry to superpixel boundaries, showing effectiveness in preserving size and shape compared to state-of-the-art methods.
Over-segmentation of an image into superpixels has become a useful tool for solving various problems in image processing and computer vision. Reflection symmetry is quite prevalent in both natural and man-made objects and is an essential cue in understanding and grouping the objects in natural scenes. Existing algorithms for estimating superpixels do not preserve the reflection symmetry of an object which leads to different sizes and shapes of superpixels across the symmetry axis. In this work, we propose an algorithm to over-segment an image through the propagation of reflection symmetry evident at the pixel level to superpixel boundaries. In order to achieve this goal, we first find the reflection symmetry in the image and represent it by a set of pairs of pixels which are mirror reflections of each other. We partition the image into superpixels while preserving this reflection symmetry through an iterative algorithm. We compare the proposed method with state-of-the-art superpixel generation methods and show the effectiveness in preserving the size and shape of superpixel boundaries across the reflection symmetry axes. We also present two applications, symmetry axes detection and unsupervised symmetric object segmentation, to illustrate the effectiveness of the proposed approach.