Hyperspectral Classification Based on Texture Feature Enhancement and Deep Belief Networks

Jiaojiao Li,Bobo Xi,Qian Du,Yunsong Li,Keyan Wang

doi:10.3390/rs10030396

Jiaojiao Li, Bobo Xi + Show 3 more

Open Access

https://doi.org/10.3390/rs10030396

Copy DOI

Journal: Remote sensing	Publication Date: Mar 4, 2018
Citations: 80	License type: CC BY 4.0

Affiliation: Xidian University, Mississippi State University

Abstract

With success of Deep Belief Networks (DBNs) in computer vision, DBN has attracted great attention in hyperspectral classification. Many deep learning based algorithms have been focused on deep feature extraction for classification improvement. Multi-features, such as texture feature, are widely utilized in classification process to enhance classification accuracy greatly. In this paper, a novel hyperspectral classification framework based on an optimal DBN and a novel texture feature enhancement (TFE) is proposed. Through band grouping, sample band selection and guided filtering, the texture features of hyperspectral data are improved. After TFE, the optimal DBN is employed on the hyperspectral reconstructed data for feature extraction and classification. Experimental results demonstrate that the proposed classification framework outperforms some state-of-the-art classification algorithms, and it can achieve outstanding hyperspectral classification performance. Furthermore, our proposed TFE method can play a significant role in improving classification accuracy.

Highlights

Hyperspectral imagery with hundreds of narrow spectral channels provides wealthy spectral information
The bands of University of Pavia can be divided into 19 groups: 1, 2, 3, 4, 5, 6, 7, 8–68, 69, 70, 71, To analyze and evaluate our proposed algorithm, which combines the texture feature enhancement (TFE) and the optimal Deep Belief Networks (DBNs) efficiently, existing algorithm, such as support vector machine (SVM) with Radial Basis Function kernel (SVM-RBF), the Radical Basis Function neural network (RBFNN) and convolutional neural networks (CNN), are employed for comparison purpose
We investigate a novel hyperspectral classification framework based on an optimal DBN algorithm

Summary

Introduction

Hyperspectral imagery with hundreds of narrow spectral channels provides wealthy spectral information. A majority of classification methods have been promoted in the last several decades to distinguish physical objects and classify each pixel into a unique land-cover label, such as maximum likelihood [5], minimum distance [6], K-nearest neighbors [7,8], random forests [9], Bayesian models [10,11], neural networks, etc., and their improvements [12,13,14,15] Among these supervised classifiers, one of the most important classifiers is kernel-based support vector machine (SVM), which can be considered as a kind of neural network. It can achieve superior hyperspectral classification accuracy via building an optimal hyperplane to best separate training samples

Methods

Results

Discussion

Conclusion