Sparse based image classification with different keypoints descriptors

Authors:
Yuanyuan Zuo;Bo Zhang
Affiliations:
State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, ...;State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, ...
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Year:
2011

Citing 7
Cited 0

Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparison of Affine Region Detectors

International Journal of Computer Vision
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

International Journal of Computer Vision
Robust Face Recognition via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Relevance feedback in region-based image retrieval

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we apply the sparse representation based algorithm to the problem of generic image classification. Keypoints with different descriptors are used as the bases of the training matrix and test samples. A learning algorithm is also presented to select the most important keypoints as the bases of the training matrix. Experiments have been done on 25 object categories selected from Caltech101 dataset, with salient region detector and different descriptors. The results show that keypoints with histogram of oriented gradients descriptor can achieve good performance on image categories which have distinctive patterns detected as keypoints. Furthermore, the base learning algorithm is useful for improving the performance while reducing the computational complexity.