Background Information Self-Learning Based Hyperspectral Target Detection

Yufei Tian,Wenning Xu,Jihai Yang,Shijun Li

doi:10.1155/2018/3502508

Yufei Tian, Wenning Xu + Show 2 more

Open Access

https://doi.org/10.1155/2018/3502508

Copy DOI

Abstract

Hyperspectral imaging has been proved as an effective way to explore the useful information behind the land objects. And it can also be adopted for biologic information extraction, by which the origin information can be acquired from the image repeatedly without contamination. In this paper we proposed a target detection method based on background self-learning to extract the biologic information from the hyperspectral images. The conventional unstructured target detectors are very difficult to estimate the background statistics accurately in either a global or local way. Considering the spatial spectral information, its performance can be further improved by avoiding the above problem. It is especially designed to extract fingerprint and tumor region from hyperspectral biologic images. The experimental results show the validity and the superiority of our method on detecting the biologic information from hyperspectral images.

Highlights

BackgroundReceived 24 August 2017; Revised 30 January 2018; Accepted 28 February 2018; Published 3 July 2018
Hyperspectral imaging has been proved as an effective way to explore the useful information behind the land objects. It can be adopted for biologic information extraction, by which the origin information can be acquired from the image repeatedly without contamination
In this paper we proposed a target detection method based on background self-learning to extract the biologic information from the hyperspectral images

Summary

Background

Received 24 August 2017; Revised 30 January 2018; Accepted 28 February 2018; Published 3 July 2018. Hyperspectral imaging has been proved as an effective way to explore the useful information behind the land objects. It can be adopted for biologic information extraction, by which the origin information can be acquired from the image repeatedly without contamination. In this paper we proposed a target detection method based on background self-learning to extract the biologic information from the hyperspectral images. The conventional unstructured target detectors are very difficult to estimate the background statistics accurately in either a global or local way. It is especially designed to extract fingerprint and tumor region from hyperspectral biologic images. The experimental results show the validity and the superiority of our method on detecting the biologic information from hyperspectral images

Introduction

Information Extraction Methods by Background Information Self-Learning

Experiment and Analysis