Back to Algorithm Ranking.

[Grayscale] Boundary Detection Benchmark: Algorithm "Boosted Edge Learning"

Piotr Dollar, Zhuowen Tu, and Serge Belongie, "Supervised Learning of Edges and Object Boundaries", IEEE Computer Vision and Pattern Recognition (CVPR), June, 2006.

In this paper, we propose a novel supervised learning algorithm for edge and object boundary detection which we refer to as Boosted Edge Learning or BEL for short. A decision of an edge point is made independently at each location in the image; a very large aperture is used providing significant context for each decision. In the learning stage, the algorithm selects and combines a large number of features across different scales in order to learn a discriminative model using an extended version of the Probabilistic Boosting Tree classification algorithm. The learning based framework is highly adaptive and there are no parameters to tune.

software

Click on an image for additional details.

#1 (119082) F=0.70
#2 (170057) F=0.66
#3 (58060) F=0.50
#4 (163085) F=0.49
#5 (42049) F=0.92
#6 (167062) F=0.67
#7 (157055) F=0.73
#8 (295087) F=0.71
#9 (24077) F=0.74
#10 (78004) F=0.79
#11 (220075) F=0.62
#12 (45096) F=0.76
#13 (38092) F=0.78
#14 (43074) F=0.66
#15 (16077) F=0.57
#16 (86000) F=0.62
#17 (101085) F=0.74
#18 (219090) F=0.71
#19 (89072) F=0.68
#20 (300091) F=0.57
#21 (126007) F=0.72
#22 (156065) F=0.66
#23 (76053) F=0.61
#24 (296007) F=0.66
#25 (175032) F=0.49
#26 (253027) F=0.63
#27 (304034) F=0.47
#28 (86016) F=0.39
#29 (103070) F=0.68
#30 (8023) F=0.41
#31 (260058) F=0.63
#32 (41033) F=0.62
#33 (291000) F=0.57
#34 (109053) F=0.61
#35 (130026) F=0.52
#36 (241004) F=0.85
#37 (108082) F=0.43
#38 (285079) F=0.71
#39 (147091) F=0.71
#40 (69040) F=0.50
#41 (14037) F=0.65
#42 (54082) F=0.54
#43 (189080) F=0.78
#44 (229036) F=0.67
#45 (62096) F=0.79
#46 (271035) F=0.73
#47 (167083) F=0.61
#48 (12084) F=0.48
#49 (69015) F=0.79
#50 (148089) F=0.68
#51 (160068) F=0.72
#52 (145086) F=0.71
#53 (216081) F=0.79
#54 (97033) F=0.69
#55 (182053) F=0.77
#56 (208001) F=0.66
#57 (19021) F=0.65
#58 (227092) F=0.75
#59 (134035) F=0.71
#60 (223061) F=0.58
#61 (253055) F=0.75
#62 (148026) F=0.52
#63 (210088) F=0.73
#64 (86068) F=0.59
#65 (3096) F=0.90
#66 (41069) F=0.68
#67 (21077) F=0.65
#68 (196073) F=0.72
#69 (108070) F=0.41
#70 (123074) F=0.57
#71 (376043) F=0.60
#72 (306005) F=0.70
#73 (38082) F=0.59
#74 (33039) F=0.61
#75 (108005) F=0.53
#76 (106024) F=0.72
#77 (302008) F=0.66
#78 (102061) F=0.62
#79 (197017) F=0.78
#80 (299086) F=0.71
#81 (37073) F=0.83
#82 (241048) F=0.70
#83 (65033) F=0.73
#84 (55073) F=0.52
#85 (66053) F=0.74
#86 (143090) F=0.69
#87 (85048) F=0.76
#88 (42012) F=0.60
#89 (351093) F=0.71
#90 (361010) F=0.73
#91 (175043) F=0.32
#92 (87046) F=0.60
#93 (105025) F=0.56
#94 (236037) F=0.51
#95 (101087) F=0.77
#96 (304074) F=0.62
#97 (296059) F=0.85
#98 (159008) F=0.59
#99 (385039) F=0.81
#100 (69020) F=0.65

Page generated on 20-Feb-2013 11:08:18.