Abstract
This paper describes several ensemble methods that combine multiple edge and orientation based histograms with support vector machine classifiers. The aim is to enhance learning speed and accuracy performance by using the chosen classical primitive filters on different edge and orientation descriptors. For efficiently describe images using these descriptors, the combination of a few basis features or edge filters are used. The stronger filter operator responds to edge-like structures, the more sensitive it to orientation. Thus, using more than one edge filter allows to capture more edge information to completely describe the structure of image content. One problem in combining these different descriptors is that the input vector becomes very large dimensionality, which can increase problems of overfitting and hinder generalization performance. The intuitively designed ensemble methods namely product, mean and majority are then used to combine support vector machines classifiers derived from the multiple orientations of edge operators. The results indicate that the ensemble methods outperform the single and naive classifiers.
| Original language | English |
|---|---|
| Title of host publication | Advances in Intelligent Systems and Computing |
| Pages | 33-43 |
| Number of pages | 11 |
| Volume | 208 AISC |
| DOIs | |
| Publication status | Published - 2013 |
| Event | 1st International Conference on Robot Intelligence Technology and Applications, RiTA 2012 - Gwangju Duration: 16 Dec 2012 → 18 Dec 2012 |
Publication series
| Name | Advances in Intelligent Systems and Computing |
|---|---|
| Volume | 208 AISC |
| ISSN (Print) | 21945357 |
Other
| Other | 1st International Conference on Robot Intelligence Technology and Applications, RiTA 2012 |
|---|---|
| City | Gwangju |
| Period | 16/12/12 → 18/12/12 |
Fingerprint
Keywords
- compass filters
- ensemble rules
- object categorization
- support vector machines
ASJC Scopus subject areas
- Computer Science(all)
- Control and Systems Engineering
Cite this
Ensembles of gradient based descriptors with derivative filters for visual object categorization. / Eqlouss, Enas A A; Abdullah, Azizi; Sheikh Abdullah, Siti Norul Huda.
Advances in Intelligent Systems and Computing. Vol. 208 AISC 2013. p. 33-43 (Advances in Intelligent Systems and Computing; Vol. 208 AISC).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Ensembles of gradient based descriptors with derivative filters for visual object categorization
AU - Eqlouss, Enas A A
AU - Abdullah, Azizi
AU - Sheikh Abdullah, Siti Norul Huda
PY - 2013
Y1 - 2013
N2 - This paper describes several ensemble methods that combine multiple edge and orientation based histograms with support vector machine classifiers. The aim is to enhance learning speed and accuracy performance by using the chosen classical primitive filters on different edge and orientation descriptors. For efficiently describe images using these descriptors, the combination of a few basis features or edge filters are used. The stronger filter operator responds to edge-like structures, the more sensitive it to orientation. Thus, using more than one edge filter allows to capture more edge information to completely describe the structure of image content. One problem in combining these different descriptors is that the input vector becomes very large dimensionality, which can increase problems of overfitting and hinder generalization performance. The intuitively designed ensemble methods namely product, mean and majority are then used to combine support vector machines classifiers derived from the multiple orientations of edge operators. The results indicate that the ensemble methods outperform the single and naive classifiers.
AB - This paper describes several ensemble methods that combine multiple edge and orientation based histograms with support vector machine classifiers. The aim is to enhance learning speed and accuracy performance by using the chosen classical primitive filters on different edge and orientation descriptors. For efficiently describe images using these descriptors, the combination of a few basis features or edge filters are used. The stronger filter operator responds to edge-like structures, the more sensitive it to orientation. Thus, using more than one edge filter allows to capture more edge information to completely describe the structure of image content. One problem in combining these different descriptors is that the input vector becomes very large dimensionality, which can increase problems of overfitting and hinder generalization performance. The intuitively designed ensemble methods namely product, mean and majority are then used to combine support vector machines classifiers derived from the multiple orientations of edge operators. The results indicate that the ensemble methods outperform the single and naive classifiers.
KW - compass filters
KW - ensemble rules
KW - object categorization
KW - support vector machines
UR - http://www.scopus.com/inward/record.url?scp=84876278772&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84876278772&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-37374-9_4
DO - 10.1007/978-3-642-37374-9_4
M3 - Conference contribution
AN - SCOPUS:84876278772
SN - 9783642373732
VL - 208 AISC
T3 - Advances in Intelligent Systems and Computing
SP - 33
EP - 43
BT - Advances in Intelligent Systems and Computing
ER -