Title | ||
---|---|---|
Incorporating geometry information with weak classifiers for improved generic visual categorization |
Abstract | ||
---|---|---|
In this paper, we improve the performance of a generic visual categorizer based on the ”bag of keypatches” approach using geometric information. More precisely, we consider a large number of simple geometrical relationships between interest points based on the scale, orientation or closeness. Each relationship leads to a weak classifier. The boosting approach is used to select from this multitude of classifiers (several millions in our case) and to combine them effectively with the original classifier. Results are shown on a new challenging 10 class dataset. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11553595_75 | ICIAP |
Keywords | Field | DocType |
simple geometrical relationship,interest point,incorporating geometry information,generic visual categorizer,original classifier,class dataset,weak classifier,large number,geometric information,improved generic visual categorization | Categorization,Boosting methods for object categorization,Pattern recognition,Computer science,Closeness,Artificial intelligence,Boosting (machine learning),Classifier (linguistics),Machine learning | Conference |
Volume | ISSN | ISBN |
3617 | 0302-9743 | 3-540-28869-4 |
Citations | PageRank | References |
1 | 0.47 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gabriela Csurka | 1 | 972 | 85.08 |
Jutta Willamowski | 2 | 52 | 12.58 |
C.R. Dance | 3 | 936 | 62.87 |
Florent Perronnin | 4 | 5448 | 291.48 |