Abstract | ||
---|---|---|
We propose a method to automatically extract a sketch of a common object structure present in a small set of real world weakly-labeled images. Applying a part-based deformable contour matching technique gives the location of repeatable contours. An initial deformable search strategy selects a set of salient, repeatable contours robust to a large range of non-rigid deformations. A contour completion technique based on a locally greedy bi-directional search strategy is adopted to merge the repeatable contour fragments for obtaining a complete shape. The output of our algorithm is used as an input to a sketch-based object-recognizer with results that are either better, or on par with those obtained with the ground truth sketches provided with the dataset. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33863-2_7 | ECCV Workshops (1) |
Keywords | Field | DocType |
initial deformable search strategy,repeatable contour fragment,automatic sketch,ground truth,complete shape,small set,common object structure present,greedy bi-directional search strategy,contour completion technique,repeatable contour,deformable object,part-based deformable contour | Computer vision,Pattern recognition,Computer science,Object structure,Ground truth,Contour matching,Artificial intelligence,Merge (version control),Small set,Salient,Sketch | Conference |
Volume | ISSN | Citations |
7583 | 0302-9743 | 10 |
PageRank | References | Authors |
0.51 | 21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Smit Marvaniya | 1 | 15 | 3.63 |
Sreyasee Bhattacharjee | 2 | 21 | 3.40 |
Venkatesh Manickavasagam | 3 | 12 | 1.21 |
Anurag Mittal | 4 | 1144 | 81.23 |