A Harmonic Mean Linear Discriminant Analysis for Robust Image Classification

10/14/2016
by   Shuai Zheng, et al.
0

Linear Discriminant Analysis (LDA) is a widely-used supervised dimensionality reduction method in computer vision and pattern recognition. In null space based LDA (NLDA), a well-known LDA extension, between-class distance is maximized in the null space of the within-class scatter matrix. However, there are some limitations in NLDA. Firstly, for many data sets, null space of within-class scatter matrix does not exist, thus NLDA is not applicable to those datasets. Secondly, NLDA uses arithmetic mean of between-class distances and gives equal consideration to all between-class distances, which makes larger between-class distances can dominate the result and thus limits the performance of NLDA. In this paper, we propose a harmonic mean based Linear Discriminant Analysis, Multi-Class Discriminant Analysis (MCDA), for image classification, which minimizes the reciprocal of weighted harmonic mean of pairwise between-class distance. More importantly, MCDA gives higher priority to maximize small between-class distances. MCDA can be extended to multi-label dimension reduction. Results on 7 single-label data sets and 4 multi-label data sets show that MCDA has consistently better performance than 10 other single-label approaches and 4 other multi-label approaches in terms of classification accuracy, macro and micro average F1 score.

READ FULL TEXT
research
04/08/2020

Saliency-based Weighted Multi-label Linear Discriminant Analysis

In this paper, we propose a new variant of Linear Discriminant Analysis ...
research
09/21/2013

Latent Fisher Discriminant Analysis

Linear Discriminant Analysis (LDA) is a well-known method for dimensiona...
research
10/14/2016

Kernel Alignment Inspired Linear Discriminant Analysis

Kernel alignment measures the degree of similarity between two kernels. ...
research
08/13/2019

Null Space Analysis for Class-Specific Discriminant Learning

In this paper, we carry out null space analysis for Class-Specific Discr...
research
09/24/2020

Self-Weighted Robust LDA for Multiclass Classification with Edge Classes

Linear discriminant analysis (LDA) is a popular technique to learn the m...
research
11/11/2020

Two-dimensional Bhattacharyya bound linear discriminant analysis with its applications

Recently proposed L2-norm linear discriminant analysis criterion via the...
research
12/06/2020

Food Classification with Convolutional Neural Networks and Multi-Class Linear Discernment Analysis

Convolutional neural networks (CNNs) have been successful in representin...

Please sign up or login with your details

Forgot password? Click here to reset