Grassmannian Discriminant Maps (GDM) for Manifold Dimensionality Reduction with Application to Image Set Classification

06/28/2018
by   Rui Wang, et al.
0

In image set classification, a considerable progress has been made by representing original image sets on Grassmann manifolds. In order to extend the advantages of the Euclidean based dimensionality reduction methods to the Grassmann Manifold, several methods have been suggested recently which jointly perform dimensionality reduction and metric learning on Grassmann manifold to improve performance. Nevertheless, when applied to complex datasets, the learned features do not exhibit enough discriminatory power. To overcome this problem, we propose a new method named Grassmannian Discriminant Maps (GDM) for manifold dimensionality reduction problems. The core of the method is a new discriminant function for metric learning and dimensionality reduction. For comparison and better understanding, we also study a simple variations to GDM. The key difference between them is the discriminant function. We experiment on data sets corresponding to three tasks: face recognition, object categorization, and hand gesture recognition to evaluate the proposed method and its simple extensions. Compared with the state of the art, the results achieved show the effectiveness of the proposed algorithm.

READ FULL TEXT
research
09/29/2008

An Information Geometric Framework for Dimensionality Reduction

This report concerns the problem of dimensionality reduction through inf...
research
11/23/2020

Manifold Partition Discriminant Analysis

We propose a novel algorithm for supervised dimensionality reduction nam...
research
12/08/2014

Web image annotation by diffusion maps manifold learning algorithm

Automatic image annotation is one of the most challenging problems in ma...
research
04/08/2020

Nonlinear Dimensionality Reduction for Data Visualization: An Unsupervised Fuzzy Rule-based Approach

Here, we propose an unsupervised fuzzy rule-based dimensionality reducti...
research
06/27/2012

Regularizers versus Losses for Nonlinear Dimensionality Reduction: A Factored View with New Convex Relaxations

We demonstrate that almost all non-parametric dimensionality reduction m...
research
08/19/2012

Trace transform based method for color image domain identification

Context categorization is a fundamental pre-requisite for multi-domain m...
research
07/31/2015

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs

State-of-the-art image-set matching techniques typically implicitly mode...

Please sign up or login with your details

Forgot password? Click here to reset