Abstract | ||
---|---|---|
This paper proposes a hybrid model for deformable template which combines alignable and non-alignable sketches. These sketches are subject to slight or considerable translations in different images. For slight translations, Wu et al [13] proposed active basis model to capture them, where each sketch is allowed to shift in position and orientation. For larger translations of sketches, [131 assumed that they follow the same distribution as sketches of natural image ensembles, which need not be explicitly modeled. But in fact, for a specified object class, the unaligned sketches follow a totally different distribution from those of natural images. We summarize these sketches by their means in the foreground mask. We treat the mean value in each direction as independent features and fit their marginal distributions on object ensemble and natural image ensemble using Gaussian distribution. The marginal distributions are combined with Active Basis into a joint probability ratio to distinguish foreground object from natural background. Experiments are conducted on 14 object classes, most of which show considerable improvement in ROC. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4761713 | ICPR |
Keywords | Field | DocType |
computational modeling,mathematical model,gaussian distribution,hidden markov models,probability,object recognition | Computer vision,Joint probability distribution,Pattern recognition,Mean value,Computer science,Object Class,Gaussian,Artificial intelligence,Hidden Markov model,Marginal distribution,Cognitive neuroscience of visual object recognition,Sketch | Conference |
Volume | Issue | ISSN |
null | null | null |
ISBN | Citations | PageRank |
978-1-4244-2175-6 | 0 | 0.34 |
References | Authors | |
6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Linjie Zhang | 1 | 2 | 2.08 |
Haifeng Gong | 2 | 298 | 16.03 |
Tianfu Wu | 3 | 331 | 26.72 |
Junyu Dong | 4 | 393 | 77.68 |