Hyperspectral imaging for food applications

Stephen Marshall, Timothy Kelman, Tong Qiao, Paul Murray, Jaime Zabalza

Research output: Contribution to conferencePaper

16 Citations (Scopus)
82 Downloads (Pure)

Abstract

Food quality analysis is a key area where reliable, nondestructive and accurate measures are required. Hyperspectral imaging is a technology which meets all of these requirements but only if appropriate signal processing techniques are implemented. In this paper, a discussion of some of these state-of-the-art processing techniques is followed by an explanation of four different applications of hyperspectral imaging for food quality analysis: shelf life estimation of baked sponges; beef quality prediction; classification of Chinese tea leaves; and classification of rice grains. The first two of these topics investigate the use of hyperspectral imaging to produce an objective measure about the quality of the food sample. The final two studies are classification problems, where an unknown sample is assigned to one of a previously defined set of classes.
Original languageEnglish
Pages2854 - 2858
Number of pages5
DOIs
Publication statusPublished - 1 Sep 2015
Event23rd European Signal Processing Conference, 2015 (EUSIPCO 2015) - Nice, France
Duration: 31 Aug 20154 Sep 2015

Conference

Conference23rd European Signal Processing Conference, 2015 (EUSIPCO 2015)
Abbreviated titleEUSIPCO 2015
CountryFrance
CityNice
Period31/08/154/09/15

Fingerprint

Food Quality
food quality
Food Analysis
image analysis
Food
beef quality
Beef
Porifera
Tea
tea
shelf life
Signal processing
Technology
rice
sampling
prediction
Processing
methodology
Hyperspectral imaging
leaves

Keywords

  • signal processing
  • image processing
  • image classification
  • spectral imaging
  • hyperspectral imaging
  • food safety
  • feature extraction
  • covariance matrices

Cite this

Marshall, S., Kelman, T., Qiao, T., Murray, P., & Zabalza, J. (2015). Hyperspectral imaging for food applications. 2854 - 2858. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France. https://doi.org/10.1109/EUSIPCO.2015.7362906
Marshall, Stephen ; Kelman, Timothy ; Qiao, Tong ; Murray, Paul ; Zabalza, Jaime. / Hyperspectral imaging for food applications. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France.5 p.
@conference{4791e14c6e5d4713a6d1698295211c44,
title = "Hyperspectral imaging for food applications",
abstract = "Food quality analysis is a key area where reliable, nondestructive and accurate measures are required. Hyperspectral imaging is a technology which meets all of these requirements but only if appropriate signal processing techniques are implemented. In this paper, a discussion of some of these state-of-the-art processing techniques is followed by an explanation of four different applications of hyperspectral imaging for food quality analysis: shelf life estimation of baked sponges; beef quality prediction; classification of Chinese tea leaves; and classification of rice grains. The first two of these topics investigate the use of hyperspectral imaging to produce an objective measure about the quality of the food sample. The final two studies are classification problems, where an unknown sample is assigned to one of a previously defined set of classes.",
keywords = "signal processing, image processing, image classification, spectral imaging, hyperspectral imaging, food safety, feature extraction, covariance matrices",
author = "Stephen Marshall and Timothy Kelman and Tong Qiao and Paul Murray and Jaime Zabalza",
note = "{\circledC} 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), EUSIPCO 2015 ; Conference date: 31-08-2015 Through 04-09-2015",
year = "2015",
month = "9",
day = "1",
doi = "10.1109/EUSIPCO.2015.7362906",
language = "English",
pages = "2854 -- 2858",

}

Marshall, S, Kelman, T, Qiao, T, Murray, P & Zabalza, J 2015, 'Hyperspectral imaging for food applications' Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France, 31/08/15 - 4/09/15, pp. 2854 - 2858. https://doi.org/10.1109/EUSIPCO.2015.7362906

Hyperspectral imaging for food applications. / Marshall, Stephen; Kelman, Timothy; Qiao, Tong; Murray, Paul; Zabalza, Jaime.

2015. 2854 - 2858 Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Hyperspectral imaging for food applications

AU - Marshall, Stephen

AU - Kelman, Timothy

AU - Qiao, Tong

AU - Murray, Paul

AU - Zabalza, Jaime

N1 - © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Food quality analysis is a key area where reliable, nondestructive and accurate measures are required. Hyperspectral imaging is a technology which meets all of these requirements but only if appropriate signal processing techniques are implemented. In this paper, a discussion of some of these state-of-the-art processing techniques is followed by an explanation of four different applications of hyperspectral imaging for food quality analysis: shelf life estimation of baked sponges; beef quality prediction; classification of Chinese tea leaves; and classification of rice grains. The first two of these topics investigate the use of hyperspectral imaging to produce an objective measure about the quality of the food sample. The final two studies are classification problems, where an unknown sample is assigned to one of a previously defined set of classes.

AB - Food quality analysis is a key area where reliable, nondestructive and accurate measures are required. Hyperspectral imaging is a technology which meets all of these requirements but only if appropriate signal processing techniques are implemented. In this paper, a discussion of some of these state-of-the-art processing techniques is followed by an explanation of four different applications of hyperspectral imaging for food quality analysis: shelf life estimation of baked sponges; beef quality prediction; classification of Chinese tea leaves; and classification of rice grains. The first two of these topics investigate the use of hyperspectral imaging to produce an objective measure about the quality of the food sample. The final two studies are classification problems, where an unknown sample is assigned to one of a previously defined set of classes.

KW - signal processing

KW - image processing

KW - image classification

KW - spectral imaging

KW - hyperspectral imaging

KW - food safety

KW - feature extraction

KW - covariance matrices

UR - http://www.eusipco2015.org/

U2 - 10.1109/EUSIPCO.2015.7362906

DO - 10.1109/EUSIPCO.2015.7362906

M3 - Paper

SP - 2854

EP - 2858

ER -

Marshall S, Kelman T, Qiao T, Murray P, Zabalza J. Hyperspectral imaging for food applications. 2015. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France. https://doi.org/10.1109/EUSIPCO.2015.7362906