The Prague Texture Segmentation Datagenerator and Benchmark - Algorithms
optimized
for

The concise description of algorithms contains hyperlinks to further information (author, algorithms details, BIB entry, WWW external page).
The algorithm features are: f1 = classification (supervised segmentation), f2 = hiearchy result (manual selection), f3 = known number of regions, f4 = [reserved].
xiaofang's
LocalGlobalGraph
version color
BIB
DOC
f1: 0
f2: 1
f3: 0
f4: 0
Xiaofang Wang, Yuxing Tang, Simon Masnou, and Liming Chen:   A Global/Local Affinity Graph for Image Segmentation

Construction of a reliable graph capturing perceptual grouping cues of an image is fundamental for graph-cut based image segmentation methods. We propose a novel sparse global/local affinity graph over superpixels of an input image to capture both short and long range grouping cues, thereby enabling perceptual grouping laws, e.g., proximity, similarity, continuity, to enter in action through a suitable graph cut algorithm. Moreover, we also evaluate three major visual features, namely color, texture and shape, for their effectiveness in perceptual segmentation and propose a simple graph fusion scheme to implement some recent findings from psychophysics which suggest combining these visual features with different emphases for perceptual grouping.

Specifically, an input image is first oversegmented into superpixels at different scales. We postulate a gravitation law based on empirical observations and divide superpixels adaptively into small, medium and large sized sets. Global grouping is achieved using medium sized superpixels through a sparse representation of superpixels' features by solving a `0-minimization problem, thereby enabling continuity or propagation of local smoothness over long range connections. Small and large sized superpixels are then used to achieve local smoothness through an adjacent graph in a given feature space, thus implementing perceptual laws, e.g., similarity and proximity. Finally, a bipartite graph is also introduced to enable propagation of grouping cues between superpixels of different scales.


List of uploaded results for 'LocalGlobalGraph' algorithm
   benchmark label version CS OS US ME NE O C CA CO CC I II EA MS RM CI GCE LCE BCE GBCE BGM SC SSC VD L AVI NVI NMI M ARI JC DC FMI WI WII NBDE
#Colour [normal] LocalGlobalGraph color 4.94 95.00 95.00 95.00 95.00 95.00 95.00 4.88 4.94 4.94 95.06 95.03 4.94 -42.59 95.05 4.94 95.12 95.06 95.18 95.12 4.94 4.88 4.88 95.06 4.94 95.04 95.25 4.75 95.09 4.81 4.75 4.87 4.87 4.87 4.87 95.07
Colour [normal] LocalGlobalGraph color 41.42 15.04 12.48 27.64 26.92 17.80 15.13 66.53 75.75 82.19 24.25 4.17 76.10 63.63 6.72 77.48 20.47 11.25 35.25 26.03 75.75 68.47 68.43 17.13 75.42 6.47 21.84 76.07 11.22 66.22 59.42 73.37 73.72 74.33 73.83 8.02
#Colour [normal] LocalGlobalGraph color 8.88 5.06 4.85 80.13 80.24 55.66 63.52 39.03 51.33 62.45 48.67 7.25 52.03 31.73 8.75 54.15 39.38 33.62 61.80 56.04 51.33 40.82 41.81 37.34 51.70 14.32 41.17 48.75 22.10 33.98 32.00 46.97 48.28 50.31 49.07 15.82