Eikonal-based vertices growing and iterative seeding for efficient graph-based segmentation

Abstract

In this paper we propose to use the Eikonal equation on graphs for generalized data clustering. We introduce a new potential function that favors the creation of homogeneous clusters together with an iterative algorithm that place seeds vertices at smart locations. Oversegmentation application shows the effectiveness of our approach and gives results comparable to the state-of-the-art methods.

SuperPatchMatch: An Algorithm for Robust Correspondences Using Superpixel Patches

“…Superpixels vs superpatches for superpixel matching. (a) and (b): two decompositions using [1] and [13]. (c) and (d): superpixel-based [14] and our superpatch-based matching results.…”

“…[14] and our superpatch-based matching results where red superpixels indicate wrong matched texture. (e) and (f): two decompositions of a natural textured image using [1] and [13]. Comparison of superpatch matching with color (g) and combination of color and texture features (h).…”

Robust shape regularity criteria for superpixel evaluation

“…Method C SRC SLIC [6] 0.438 ± 0.111 0.518 ± 0.072 ERGC [15] 0.367 ± 0.040 0.456 ± 0.015 WP [7] 0.483 ± 0.076 0.559 ± 0.043 LSC [8] 0.228 ± 0.046 0.327 ± 0.035 SCALP [11] 0.515 ± 0.115 0.586 ± 0.073…”

“…ERGC [15] WP [7] LSC [8] SCALP [11] Fig. 8: Regularity evolution of noisy superpixels computed from [6] for several compactness settings on the BSD.…”

“…For most superpixel-based applications such as object recognition [1,2], labeling [3] or tracking [4,5], the use of regular decompositions [6,7,8,9,10,11] where superpixels roughly have the same size and regular shapes is necessary. With such regularity, accurate superpixel features can be computed and relevant information can be extracted from their boundaries, while with irregular decompositions [12,13,14,15,16], superpixels can have different sizes, noisy boundaries and stretched shapes.…”