Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread

Marjatta Salmenkallio-Marttila (Corresponding Author), Katariina Roininen, J. T. Lindgren, Juho Rousu, Karin Autio, Liisa Lähteenmäki

Research output: Contribution to journalArticleScientificpeer-review

10 Citations (Scopus)

Abstract

The aim was to study whether machine learning can be applied in analysing microstructure of food from microscopy images and whether the state of macromolecules, protein and starch, can be related to sensory mouthfeel. Addition of gluten and transglutaminase modified the microstructure and mouthfeel of five oat bread samples. Light microscopy, instrumental texture profile analysis and descriptive sensory analysis were used to analyse the test breads. Digital image analysis was used to obtain numerical data on starch and protein phases in the breads. Degree of starch gelatinization and protein network properties were extracted from microscopy images by expert ratings. Many of the bread sensory properties could be predicted using instrumental texture and image analysis features. Machine learning of degree of starch gelatinization and protein network structure properties from expert classified microscope images was studied. Color histograms and co‐occurrence matrix statistics were suitable preprocessing techniques for the images. In both starch gelatinization and protein network structure classification, the prediction error of an induced model tree was lower than the standard deviation between independent predictions given by experts.
Original languageEnglish
Pages (from-to)225-250
JournalJournal of Texture Studies
Volume35
Issue number3
DOIs
Publication statusPublished - 2004
MoE publication typeA1 Journal article-refereed

Fingerprint

mouthfeel
artificial intelligence
Bread
Starch
breads
microstructure
oats
starch
gelatinization
Microscopy
Proteins
proteins
microscopy
texture
image analysis
methodology
Transglutaminases
prediction
Glutens
protein-glutamine gamma-glutamyltransferase

Cite this

Salmenkallio-Marttila, M., Roininen, K., Lindgren, J. T., Rousu, J., Autio, K., & Lähteenmäki, L. (2004). Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread. Journal of Texture Studies, 35(3), 225-250. https://doi.org/10.1111/j.1745-4603.2004.tb00835.x
Salmenkallio-Marttila, Marjatta ; Roininen, Katariina ; Lindgren, J. T. ; Rousu, Juho ; Autio, Karin ; Lähteenmäki, Liisa. / Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread. In: Journal of Texture Studies. 2004 ; Vol. 35, No. 3. pp. 225-250.
@article{16487c516e7f4b5fa8cc243ebef745d8,
title = "Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread",
abstract = "The aim was to study whether machine learning can be applied in analysing microstructure of food from microscopy images and whether the state of macromolecules, protein and starch, can be related to sensory mouthfeel. Addition of gluten and transglutaminase modified the microstructure and mouthfeel of five oat bread samples. Light microscopy, instrumental texture profile analysis and descriptive sensory analysis were used to analyse the test breads. Digital image analysis was used to obtain numerical data on starch and protein phases in the breads. Degree of starch gelatinization and protein network properties were extracted from microscopy images by expert ratings. Many of the bread sensory properties could be predicted using instrumental texture and image analysis features. Machine learning of degree of starch gelatinization and protein network structure properties from expert classified microscope images was studied. Color histograms and co‐occurrence matrix statistics were suitable preprocessing techniques for the images. In both starch gelatinization and protein network structure classification, the prediction error of an induced model tree was lower than the standard deviation between independent predictions given by experts.",
author = "Marjatta Salmenkallio-Marttila and Katariina Roininen and Lindgren, {J. T.} and Juho Rousu and Karin Autio and Liisa L{\"a}hteenm{\"a}ki",
year = "2004",
doi = "10.1111/j.1745-4603.2004.tb00835.x",
language = "English",
volume = "35",
pages = "225--250",
journal = "Journal of Texture Studies",
issn = "0022-4901",
publisher = "Wiley-Blackwell",
number = "3",

}

Salmenkallio-Marttila, M, Roininen, K, Lindgren, JT, Rousu, J, Autio, K & Lähteenmäki, L 2004, 'Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread', Journal of Texture Studies, vol. 35, no. 3, pp. 225-250. https://doi.org/10.1111/j.1745-4603.2004.tb00835.x

Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread. / Salmenkallio-Marttila, Marjatta (Corresponding Author); Roininen, Katariina; Lindgren, J. T.; Rousu, Juho; Autio, Karin; Lähteenmäki, Liisa.

In: Journal of Texture Studies, Vol. 35, No. 3, 2004, p. 225-250.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread

AU - Salmenkallio-Marttila, Marjatta

AU - Roininen, Katariina

AU - Lindgren, J. T.

AU - Rousu, Juho

AU - Autio, Karin

AU - Lähteenmäki, Liisa

PY - 2004

Y1 - 2004

N2 - The aim was to study whether machine learning can be applied in analysing microstructure of food from microscopy images and whether the state of macromolecules, protein and starch, can be related to sensory mouthfeel. Addition of gluten and transglutaminase modified the microstructure and mouthfeel of five oat bread samples. Light microscopy, instrumental texture profile analysis and descriptive sensory analysis were used to analyse the test breads. Digital image analysis was used to obtain numerical data on starch and protein phases in the breads. Degree of starch gelatinization and protein network properties were extracted from microscopy images by expert ratings. Many of the bread sensory properties could be predicted using instrumental texture and image analysis features. Machine learning of degree of starch gelatinization and protein network structure properties from expert classified microscope images was studied. Color histograms and co‐occurrence matrix statistics were suitable preprocessing techniques for the images. In both starch gelatinization and protein network structure classification, the prediction error of an induced model tree was lower than the standard deviation between independent predictions given by experts.

AB - The aim was to study whether machine learning can be applied in analysing microstructure of food from microscopy images and whether the state of macromolecules, protein and starch, can be related to sensory mouthfeel. Addition of gluten and transglutaminase modified the microstructure and mouthfeel of five oat bread samples. Light microscopy, instrumental texture profile analysis and descriptive sensory analysis were used to analyse the test breads. Digital image analysis was used to obtain numerical data on starch and protein phases in the breads. Degree of starch gelatinization and protein network properties were extracted from microscopy images by expert ratings. Many of the bread sensory properties could be predicted using instrumental texture and image analysis features. Machine learning of degree of starch gelatinization and protein network structure properties from expert classified microscope images was studied. Color histograms and co‐occurrence matrix statistics were suitable preprocessing techniques for the images. In both starch gelatinization and protein network structure classification, the prediction error of an induced model tree was lower than the standard deviation between independent predictions given by experts.

U2 - 10.1111/j.1745-4603.2004.tb00835.x

DO - 10.1111/j.1745-4603.2004.tb00835.x

M3 - Article

VL - 35

SP - 225

EP - 250

JO - Journal of Texture Studies

JF - Journal of Texture Studies

SN - 0022-4901

IS - 3

ER -