Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging

Sara Sharifzadeh, Line H. Clemmensen, Hanne Løje, Bjarne K. Ersbøll

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

2 Citations (Scopus)

Abstract

Multispectral imaging is increasingly being used for quality assessment of food items due to its non-invasive benefits. In this paper, we investigate the use of multispectral images of pre-fried carrots, to detect changes over a period of 14 days. The idea is to distinguish changes in quality from spectral images of visible and NIR bands. High dimensional feature vectors were formed from all possible ratios of spectral bands in 9 different percentiles per piece of carrot. We propose to use a multiple hypothesis testing technique based on the Benjamini-Hachberg (BH) method to distinguish possible significant changes in features during the inspection days. Discrimination by the SVM classifier supported these results. Additionally, 2-sided t-tests on the predictions of the elastic-net regressions were carried out to compare our results with previous studies on fried carrots. The experimental results showed that the most significant changes occured in day 2 and day 14.
Original languageEnglish
Title of host publicationImage Analysis. SCIA 2013. Lecture Notes in Computer Science
EditorsJ K Kämäräinen, M Koskela
Place of Publication Berlin, Heidelberg
PublisherSpringer
Pages620-629
Volume7944
ISBN (Electronic)978-3-642-38886-6
ISBN (Print)978-3-642-38885-9
Publication statusPublished - 2013
Externally publishedYes
Event18th Scandinavian Conference: Scandinavian Conference on Image Analysis - Espoo, Finland
Duration: 17 Jun 201320 Jun 2013
Conference number: 18

Conference

Conference18th Scandinavian Conference
Abbreviated titleSCIA 2013
CountryFinland
CityEspoo
Period17/06/1320/06/13

Fingerprint

multispectral image
hypothesis testing
food
prediction
inspection
test
spectral band
method

Cite this

Sharifzadeh, S., Clemmensen, L. H., Løje, H., & Ersbøll, B. K. (2013). Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging. In J. K. Kämäräinen, & M. Koskela (Eds.), Image Analysis. SCIA 2013. Lecture Notes in Computer Science (Vol. 7944, pp. 620-629). Berlin, Heidelberg: Springer.

Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging. / Sharifzadeh, Sara; Clemmensen, Line H.; Løje, Hanne; Ersbøll, Bjarne K.

Image Analysis. SCIA 2013. Lecture Notes in Computer Science. ed. / J K Kämäräinen; M Koskela. Vol. 7944 Berlin, Heidelberg : Springer, 2013. p. 620-629.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Sharifzadeh, S, Clemmensen, LH, Løje, H & Ersbøll, BK 2013, Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging. in JK Kämäräinen & M Koskela (eds), Image Analysis. SCIA 2013. Lecture Notes in Computer Science. vol. 7944, Springer, Berlin, Heidelberg, pp. 620-629, 18th Scandinavian Conference, Espoo, Finland, 17/06/13.
Sharifzadeh S, Clemmensen LH, Løje H, Ersbøll BK. Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging. In Kämäräinen JK, Koskela M, editors, Image Analysis. SCIA 2013. Lecture Notes in Computer Science. Vol. 7944. Berlin, Heidelberg: Springer. 2013. p. 620-629
Sharifzadeh, Sara ; Clemmensen, Line H. ; Løje, Hanne ; Ersbøll, Bjarne K. / Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging. Image Analysis. SCIA 2013. Lecture Notes in Computer Science. editor / J K Kämäräinen ; M Koskela. Vol. 7944 Berlin, Heidelberg : Springer, 2013. pp. 620-629
@inproceedings{b50e80b0b24a490dbad2dc1dc02eb917,
title = "Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging",
abstract = "Multispectral imaging is increasingly being used for quality assessment of food items due to its non-invasive benefits. In this paper, we investigate the use of multispectral images of pre-fried carrots, to detect changes over a period of 14 days. The idea is to distinguish changes in quality from spectral images of visible and NIR bands. High dimensional feature vectors were formed from all possible ratios of spectral bands in 9 different percentiles per piece of carrot. We propose to use a multiple hypothesis testing technique based on the Benjamini-Hachberg (BH) method to distinguish possible significant changes in features during the inspection days. Discrimination by the SVM classifier supported these results. Additionally, 2-sided t-tests on the predictions of the elastic-net regressions were carried out to compare our results with previous studies on fried carrots. The experimental results showed that the most significant changes occured in day 2 and day 14.",
author = "Sara Sharifzadeh and Clemmensen, {Line H.} and Hanne L{\o}je and Ersb{\o}ll, {Bjarne K.}",
year = "2013",
language = "English",
isbn = "978-3-642-38885-9",
volume = "7944",
pages = "620--629",
editor = "K{\"a}m{\"a}r{\"a}inen, {J K} and M Koskela",
booktitle = "Image Analysis. SCIA 2013. Lecture Notes in Computer Science",
publisher = "Springer",

}

TY - GEN

T1 - Statistical Quality Assessment of Pre-fried Carrots Using Multispectral Imaging

AU - Sharifzadeh, Sara

AU - Clemmensen, Line H.

AU - Løje, Hanne

AU - Ersbøll, Bjarne K.

PY - 2013

Y1 - 2013

N2 - Multispectral imaging is increasingly being used for quality assessment of food items due to its non-invasive benefits. In this paper, we investigate the use of multispectral images of pre-fried carrots, to detect changes over a period of 14 days. The idea is to distinguish changes in quality from spectral images of visible and NIR bands. High dimensional feature vectors were formed from all possible ratios of spectral bands in 9 different percentiles per piece of carrot. We propose to use a multiple hypothesis testing technique based on the Benjamini-Hachberg (BH) method to distinguish possible significant changes in features during the inspection days. Discrimination by the SVM classifier supported these results. Additionally, 2-sided t-tests on the predictions of the elastic-net regressions were carried out to compare our results with previous studies on fried carrots. The experimental results showed that the most significant changes occured in day 2 and day 14.

AB - Multispectral imaging is increasingly being used for quality assessment of food items due to its non-invasive benefits. In this paper, we investigate the use of multispectral images of pre-fried carrots, to detect changes over a period of 14 days. The idea is to distinguish changes in quality from spectral images of visible and NIR bands. High dimensional feature vectors were formed from all possible ratios of spectral bands in 9 different percentiles per piece of carrot. We propose to use a multiple hypothesis testing technique based on the Benjamini-Hachberg (BH) method to distinguish possible significant changes in features during the inspection days. Discrimination by the SVM classifier supported these results. Additionally, 2-sided t-tests on the predictions of the elastic-net regressions were carried out to compare our results with previous studies on fried carrots. The experimental results showed that the most significant changes occured in day 2 and day 14.

M3 - Conference proceeding

SN - 978-3-642-38885-9

VL - 7944

SP - 620

EP - 629

BT - Image Analysis. SCIA 2013. Lecture Notes in Computer Science

A2 - Kämäräinen, J K

A2 - Koskela, M

PB - Springer

CY - Berlin, Heidelberg

ER -