Publication detail

An Ensemble Template Algorithm for Extracting Targets from Blurred Infrared Images

FU, D. YU, X. TONG, H. ŘÍHA, K.

Original Title

An Ensemble Template Algorithm for Extracting Targets from Blurred Infrared Images

English Title

An Ensemble Template Algorithm for Extracting Targets from Blurred Infrared Images

Type

journal article in Web of Science

Language

en

Original Abstract

In this paper, an ensemble template algorithm is proposed to extract targets from blurred infrared images. First, the image pixels are divided according to their grey values into three pixel sets, a target set, a background set and the third set without class label. Second, the neighbourhood statistical characteristics for each pixel are calculated as its template features. Third, ensemble detectors are designed using target pixels and background pixels based on their template features, and these ensemble detectors are used to detect the third pixel set. To evaluate the performance of the proposed extraction algorithm, this paper compares the ensemble template with other extraction algorithms using blurred infrared image of hand trace. Experimental results show that the ensemble template algorithm proposed in this paper exhibits better extraction performance.

English abstract

In this paper, an ensemble template algorithm is proposed to extract targets from blurred infrared images. First, the image pixels are divided according to their grey values into three pixel sets, a target set, a background set and the third set without class label. Second, the neighbourhood statistical characteristics for each pixel are calculated as its template features. Third, ensemble detectors are designed using target pixels and background pixels based on their template features, and these ensemble detectors are used to detect the third pixel set. To evaluate the performance of the proposed extraction algorithm, this paper compares the ensemble template with other extraction algorithms using blurred infrared image of hand trace. Experimental results show that the ensemble template algorithm proposed in this paper exhibits better extraction performance.

Keywords

Target extraction, Blurred infrared image, Ensemble template, Statistical characteristics

RIV year

2014

Released

01.02.2014

Publisher

Elsevier GmbH

ISBN

0030-4026

Periodical

OPTIK

Year of study

125

Number

3

State

DE

Pages from

954

Pages to

957

Pages count

4

Documents

BibTex


@article{BUT104404,
  author="Dongmei {Fu} and Xiao {Yu} and Hejun {Tong} and Kamil {Říha}",
  title="An Ensemble Template Algorithm for Extracting Targets from Blurred Infrared Images",
  annote="In this paper, an ensemble template algorithm is proposed to extract targets from blurred infrared images. First, the image pixels are divided according to their grey values into three pixel sets, a target set, a background set and the third set without class label. Second, the neighbourhood statistical characteristics for each pixel are calculated as its template features. Third, ensemble detectors are designed using target pixels and background pixels based on their template features, and these ensemble detectors are used to detect the third pixel set. To evaluate the performance of the proposed extraction algorithm, this paper compares the ensemble template with other extraction algorithms using blurred infrared image of hand trace. Experimental results show that the ensemble template algorithm proposed in this paper exhibits better extraction performance.",
  address="Elsevier GmbH",
  chapter="104404",
  doi="10.1016/j.ijleo.2013.07.130",
  institution="Elsevier GmbH",
  number="3",
  volume="125",
  year="2014",
  month="february",
  pages="954--957",
  publisher="Elsevier GmbH",
  type="journal article in Web of Science"
}