Abstract
In this paper, we propose a novel subspace learning algorithm called Local Feature Discriminant Projection (LFDP) for supervised dimensionality reduction of local features. LFDP is able to efficiently seek a subspace to improve the discriminability of local features for classification. We make three novel contributions. First, the proposed LFDP is a general supervised subspace learning algorithm which provides an efficient way for dimensionality reduction of large-scale local feature descriptors. Second, we introduce the Differential Scatter Discriminant Criterion (DSDC) to the subspace learning of local feature descriptors which avoids the matrix singularity problem. Third, we propose a generalized orthogonalization method to impose on projections, leading to a more compact and less redundant subspace. Extensive experimental validation on three benchmark datasets including UIUC-Sports, Scene-15 and MIT Indoor demonstrates that the proposed LFDP outperforms other dimensionality reduction methods and achieves state-of-the-art performance for image classification.
Original language | English |
---|---|
Pages (from-to) | 1908-1914 |
Number of pages | 7 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 38 |
Issue number | 9 |
Early online date | 4 Nov 2015 |
DOIs | |
Publication status | Published - 1 Sep 2016 |
Keywords
- image classification
- Dimensionality reduction
- local feature
- image-to-class distance
- fisher vector