Back to Algorithm Ranking.
[Grayscale] Boundary Detection Benchmark: Algorithm "Segmentation Induced by Scale Invariance"
Segmentation Induced by Scale Invariance
Stella X. Yu
IEEE Conference on Computer Vision and Pattern Recognition, San Diego, 20-26 June 2005
Perceptual organization is scale-invariant. In turn, a segmentation that
separates features consistently at all scales is the desired one that reveals
the underlying structural organization of an image. Addressing cross-scale
correspondence with interior pixels, we develop this intuition into a general
segmenter that handles texture and illusory contours through edges entirely
without any explicit characterization of texture or curvilinearity.
Experimental results demonstrate that our method not only performs on par with
either texture segmentation or boundary completion methods on their specialized
examples, but also works well on a variety of real images.
See Stella Yu's page for more details.
Click on an image for additional details.
#1 (119082) F=0.44
|
|
#2 (170057) F=0.43
|
|
#3 (58060) F=0.44
|
|
#4 (163085) F=0.46
|
|
#5 (42049) F=0.76
|
|
#6 (167062) F=0.74
|
|
#7 (157055) F=0.55
|
|
#8 (295087) F=0.50
|
|
#9 (24077) F=0.39
|
|
#10 (78004) F=0.50
|
|
#11 (220075) F=0.44
|
|
#12 (45096) F=0.50
|
|
#13 (38092) F=0.60
|
|
#14 (43074) F=0.48
|
|
#15 (16077) F=0.42
|
|
#16 (86000) F=0.47
|
|
#17 (101085) F=0.70
|
|
#18 (219090) F=0.59
|
|
#19 (89072) F=0.49
|
|
#20 (300091) F=0.67
|
|
#21 (126007) F=0.49
|
|
#22 (156065) F=0.54
|
|
#23 (76053) F=0.51
|
|
#24 (296007) F=0.58
|
|
#25 (175032) F=0.39
|
|
#26 (253027) F=0.41
|
|
#27 (304034) F=0.55
|
|
#28 (86016) F=0.44
|
|
#29 (103070) F=0.49
|
|
#30 (8023) F=0.37
|
|
#31 (260058) F=0.63
|
|
#32 (41033) F=0.63
|
|
#33 (291000) F=0.40
|
|
#34 (109053) F=0.47
|
|
#35 (130026) F=0.30
|
|
#36 (241004) F=0.64
|
|
#37 (108082) F=0.33
|
|
#38 (285079) F=0.50
|
|
#39 (147091) F=0.61
|
|
#40 (69040) F=0.37
|
|
#41 (14037) F=0.55
|
|
#42 (54082) F=0.40
|
|
#43 (189080) F=0.69
|
|
#44 (229036) F=0.51
|
|
#45 (62096) F=0.72
|
|
#46 (271035) F=0.44
|
|
#47 (167083) F=0.63
|
|
#48 (12084) F=0.30
|
|
#49 (69015) F=0.48
|
|
#50 (148089) F=0.48
|
|
#51 (160068) F=0.40
|
|
#52 (145086) F=0.42
|
|
#53 (216081) F=0.53
|
|
#54 (97033) F=0.57
|
|
#55 (182053) F=0.44
|
|
#56 (208001) F=0.47
|
|
#57 (19021) F=0.49
|
|
#58 (227092) F=0.47
|
|
#59 (134035) F=0.47
|
|
#60 (223061) F=0.53
|
|
#61 (253055) F=0.36
|
|
#62 (148026) F=0.62
|
|
#63 (210088) F=0.44
|
|
#64 (86068) F=0.51
|
|
#65 (3096) F=0.82
|
|
#66 (41069) F=0.55
|
|
#67 (21077) F=0.40
|
|
#68 (196073) F=0.50
|
|
#69 (108070) F=0.29
|
|
#70 (123074) F=0.49
|
|
#71 (376043) F=0.47
|
|
#72 (306005) F=0.61
|
|
#73 (38082) F=0.50
|
|
#74 (33039) F=0.58
|
|
#75 (108005) F=0.44
|
|
#76 (106024) F=0.60
|
|
#77 (302008) F=0.59
|
|
#78 (102061) F=0.45
|
|
#79 (197017) F=0.56
|
|
#80 (299086) F=0.53
|
|
#81 (37073) F=0.51
|
|
#82 (241048) F=0.48
|
|
#83 (65033) F=0.51
|
|
#84 (55073) F=0.41
|
|
#85 (66053) F=0.50
|
|
#86 (143090) F=0.63
|
|
#87 (85048) F=0.58
|
|
#88 (42012) F=0.51
|
|
#89 (351093) F=0.49
|
|
#90 (361010) F=0.52
|
|
#91 (175043) F=0.35
|
|
#92 (87046) F=0.37
|
|
#93 (105025) F=0.45
|
|
#94 (236037) F=0.31
|
|
#95 (101087) F=0.59
|
|
#96 (304074) F=0.52
|
|
#97 (296059) F=0.77
|
|
#98 (159008) F=0.53
|
|
#99 (385039) F=0.51
|
|
#100 (69020) F=0.50
|
|
Page generated on 20-Feb-2013 11:08:22.