Abstract | ||
---|---|---|
An object detection method from line drawings is presented. The method adopts the local neighborhood structure as the elementary descriptor, which is formed by grouping several nearest neighbor lines/curves around one reference. With this representation, both the appearance and the geometric structure of the line drawing are well described. The detection algorithm is a hypothesis-test scheme. The top k most similar local structures in the drawing are firstly obtained for each local structure of the model, and the transformation parameters are estimated for each of the k candidates, such as object center, scale and rotation factors. By treating each estimation result as a point in the parameter space, a dense region around the ground truth is then formed provided that there exist a model in the drawing. The mean shift method is used to detect the dense regions, and the significant modes are accepted as the occurrence of object instances. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.patcog.2009.11.022 | Pattern Recognition |
Keywords | Field | DocType |
shape detection,similar local structure,object instance,mean shift method,local neighborhood structure,geometric structure,object detection,mean shift,object center,line drawing,dense region,object detection method,local structure,ground truth,hypothesis test,parameter space,nearest neighbor | Scale factor,k-nearest neighbors algorithm,Object detection,Pattern recognition,Algorithm,Ground truth,Parameter space,Artificial intelligence,Mean-shift,Mathematics,Line drawings,Statistical hypothesis testing | Journal |
Volume | Issue | ISSN |
43 | 5 | Pattern Recognition |
Citations | PageRank | References |
9 | 0.48 | 22 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rujie Liu | 1 | 147 | 15.49 |
Yuehong Wang | 2 | 72 | 4.66 |
Takayuki Baba | 3 | 77 | 8.19 |
Daiki Masumoto | 4 | 76 | 6.33 |