IEICE TRANSACTIONS on Information
View-Based Object Recognition Using ND Tensor Supervised Neighborhood Embedding
Summary :
In this paper, we propose N-Dimensional (ND) Tensor Supervised Neighborhood Embedding (ND TSNE) for discriminant feature representation, which is used for view-based object recognition. ND TSNE uses a general Nth order tensor discriminant and neighborhood-embedding analysis approach for object representation. The benefits of ND TSNE include: (1) a natural way of representing data without losing structure information, i.e., the information about the relative positions of pixels or regions; (2) a reduction in the small sample size problem, which occurs in conventional supervised learning because the number of training samples is much less than the dimensionality of the feature space; (3) preserving a neighborhood structure in tensor feature space for object recognition and a good convergence property in training procedure. With Tensor-subspace features, the random forests is used as a multi-way classifier for object recognition, which is much easier for training and testing compared with multi-way SVM. We demonstrate the performance advantages of our proposed approach over existing techniques using experiments on the COIL-100 and the ETH-80 datasets.
- Publication
- IEICE TRANSACTIONS on Information Vol.E95-D No.3 pp.835-843
- Publication Date
- 2012/03/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E95.D.835
- Type of Manuscript
- PAPER
- Category
- Pattern Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Xian-Hua HAN, Yen-Wei CHEN, Xiang RUAN, "View-Based Object Recognition Using ND Tensor Supervised Neighborhood Embedding" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 3, pp. 835-843, March 2012, doi: 10.1587/transinf.E95.D.835.
Abstract: In this paper, we propose N-Dimensional (ND) Tensor Supervised Neighborhood Embedding (ND TSNE) for discriminant feature representation, which is used for view-based object recognition. ND TSNE uses a general Nth order tensor discriminant and neighborhood-embedding analysis approach for object representation. The benefits of ND TSNE include: (1) a natural way of representing data without losing structure information, i.e., the information about the relative positions of pixels or regions; (2) a reduction in the small sample size problem, which occurs in conventional supervised learning because the number of training samples is much less than the dimensionality of the feature space; (3) preserving a neighborhood structure in tensor feature space for object recognition and a good convergence property in training procedure. With Tensor-subspace features, the random forests is used as a multi-way classifier for object recognition, which is much easier for training and testing compared with multi-way SVM. We demonstrate the performance advantages of our proposed approach over existing techniques using experiments on the COIL-100 and the ETH-80 datasets.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.835/_p
Copy
@ARTICLE{e95-d_3_835,
author={Xian-Hua HAN, Yen-Wei CHEN, Xiang RUAN, },
journal={IEICE TRANSACTIONS on Information},
title={View-Based Object Recognition Using ND Tensor Supervised Neighborhood Embedding},
year={2012},
volume={E95-D},
number={3},
pages={835-843},
abstract={In this paper, we propose N-Dimensional (ND) Tensor Supervised Neighborhood Embedding (ND TSNE) for discriminant feature representation, which is used for view-based object recognition. ND TSNE uses a general Nth order tensor discriminant and neighborhood-embedding analysis approach for object representation. The benefits of ND TSNE include: (1) a natural way of representing data without losing structure information, i.e., the information about the relative positions of pixels or regions; (2) a reduction in the small sample size problem, which occurs in conventional supervised learning because the number of training samples is much less than the dimensionality of the feature space; (3) preserving a neighborhood structure in tensor feature space for object recognition and a good convergence property in training procedure. With Tensor-subspace features, the random forests is used as a multi-way classifier for object recognition, which is much easier for training and testing compared with multi-way SVM. We demonstrate the performance advantages of our proposed approach over existing techniques using experiments on the COIL-100 and the ETH-80 datasets.},
keywords={},
doi={10.1587/transinf.E95.D.835},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - View-Based Object Recognition Using ND Tensor Supervised Neighborhood Embedding
T2 - IEICE TRANSACTIONS on Information
SP - 835
EP - 843
AU - Xian-Hua HAN
AU - Yen-Wei CHEN
AU - Xiang RUAN
PY - 2012
DO - 10.1587/transinf.E95.D.835
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2012
AB - In this paper, we propose N-Dimensional (ND) Tensor Supervised Neighborhood Embedding (ND TSNE) for discriminant feature representation, which is used for view-based object recognition. ND TSNE uses a general Nth order tensor discriminant and neighborhood-embedding analysis approach for object representation. The benefits of ND TSNE include: (1) a natural way of representing data without losing structure information, i.e., the information about the relative positions of pixels or regions; (2) a reduction in the small sample size problem, which occurs in conventional supervised learning because the number of training samples is much less than the dimensionality of the feature space; (3) preserving a neighborhood structure in tensor feature space for object recognition and a good convergence property in training procedure. With Tensor-subspace features, the random forests is used as a multi-way classifier for object recognition, which is much easier for training and testing compared with multi-way SVM. We demonstrate the performance advantages of our proposed approach over existing techniques using experiments on the COIL-100 and the ETH-80 datasets.
ER -
English
