Back to Algorithm Ranking.
[Grayscale] Boundary Detection Benchmark: Algorithm "Brightness / Texture Gradients"
This algorithm uses a combination of local brightness and texture
gradients to detect boundaries. The gradients are combined with a
logistic to model the posterior probability of a boundary. Each
gradient is computed as the chi-squared difference in the distribution
of some feature in two half discs centered at a pixel and divided in
half at the putative boundary orientation. The brightness gradient is
given by the difference in luminance distributions. The texture
gradient is given by the difference in texton distributions. Textons
are computed by clustering filterbank responses using k-means, so that
they model the joint distribution of filter responses. The filters
are standard even- and odd-symmetric quadrature pair elongated linear
filters. See our NIPS and PAMI papers in the Grouping
area of the Berkeley Vision
Group web pages for additional details.
Click on an image for additional details.
#1 (119082) F=0.73
|
|
#2 (170057) F=0.68
|
|
#3 (58060) F=0.52
|
|
#4 (163085) F=0.48
|
|
#5 (42049) F=0.86
|
|
#6 (167062) F=0.76
|
|
#7 (157055) F=0.75
|
|
#8 (295087) F=0.73
|
|
#9 (24077) F=0.73
|
|
#10 (78004) F=0.79
|
|
#11 (220075) F=0.62
|
|
#12 (45096) F=0.75
|
|
#13 (38092) F=0.74
|
|
#14 (43074) F=0.65
|
|
#15 (16077) F=0.54
|
|
#16 (86000) F=0.70
|
|
#17 (101085) F=0.75
|
|
#18 (219090) F=0.69
|
|
#19 (89072) F=0.70
|
|
#20 (300091) F=0.75
|
|
#21 (126007) F=0.74
|
|
#22 (156065) F=0.61
|
|
#23 (76053) F=0.63
|
|
#24 (296007) F=0.62
|
|
#25 (175032) F=0.59
|
|
#26 (253027) F=0.73
|
|
#27 (304034) F=0.41
|
|
#28 (86016) F=0.50
|
|
#29 (103070) F=0.61
|
|
#30 (8023) F=0.33
|
|
#31 (260058) F=0.67
|
|
#32 (41033) F=0.65
|
|
#33 (291000) F=0.56
|
|
#34 (109053) F=0.59
|
|
#35 (130026) F=0.52
|
|
#36 (241004) F=0.79
|
|
#37 (108082) F=0.39
|
|
#38 (285079) F=0.71
|
|
#39 (147091) F=0.76
|
|
#40 (69040) F=0.51
|
|
#41 (14037) F=0.61
|
|
#42 (54082) F=0.57
|
|
#43 (189080) F=0.79
|
|
#44 (229036) F=0.73
|
|
#45 (62096) F=0.80
|
|
#46 (271035) F=0.70
|
|
#47 (167083) F=0.61
|
|
#48 (12084) F=0.50
|
|
#49 (69015) F=0.78
|
|
#50 (148089) F=0.70
|
|
#51 (160068) F=0.79
|
|
#52 (145086) F=0.68
|
|
#53 (216081) F=0.78
|
|
#54 (97033) F=0.71
|
|
#55 (182053) F=0.75
|
|
#56 (208001) F=0.66
|
|
#57 (19021) F=0.64
|
|
#58 (227092) F=0.76
|
|
#59 (134035) F=0.73
|
|
#60 (223061) F=0.65
|
|
#61 (253055) F=0.66
|
|
#62 (148026) F=0.52
|
|
#63 (210088) F=0.73
|
|
#64 (86068) F=0.62
|
|
#65 (3096) F=0.88
|
|
#66 (41069) F=0.70
|
|
#67 (21077) F=0.69
|
|
#68 (196073) F=0.81
|
|
#69 (108070) F=0.39
|
|
#70 (123074) F=0.55
|
|
#71 (376043) F=0.57
|
|
#72 (306005) F=0.69
|
|
#73 (38082) F=0.62
|
|
#74 (33039) F=0.61
|
|
#75 (108005) F=0.49
|
|
#76 (106024) F=0.72
|
|
#77 (302008) F=0.64
|
|
#78 (102061) F=0.54
|
|
#79 (197017) F=0.81
|
|
#80 (299086) F=0.74
|
|
#81 (37073) F=0.81
|
|
#82 (241048) F=0.69
|
|
#83 (65033) F=0.69
|
|
#84 (55073) F=0.57
|
|
#85 (66053) F=0.75
|
|
#86 (143090) F=0.69
|
|
#87 (85048) F=0.75
|
|
#88 (42012) F=0.56
|
|
#89 (351093) F=0.73
|
|
#90 (361010) F=0.73
|
|
#91 (175043) F=0.38
|
|
#92 (87046) F=0.58
|
|
#93 (105025) F=0.57
|
|
#94 (236037) F=0.41
|
|
#95 (101087) F=0.75
|
|
#96 (304074) F=0.64
|
|
#97 (296059) F=0.87
|
|
#98 (159008) F=0.58
|
|
#99 (385039) F=0.77
|
|
#100 (69020) F=0.64
|
|
Page generated on 20-Feb-2013 11:08:19.