Standard

Determination of fat and total protein content in milk using conventional digital imaging. / Kucheryavskiy, Sergey; Melenteva, Anastasiia; Bogomolov, Andrey.

в: Talanta, Том 121, 01.04.2014, стр. 144-152.

Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование

Harvard

Kucheryavskiy, S, Melenteva, A & Bogomolov, A 2014, 'Determination of fat and total protein content in milk using conventional digital imaging', Talanta, Том. 121, стр. 144-152. https://doi.org/10.1016/j.talanta.2013.12.055

APA

Kucheryavskiy, S., Melenteva, A., & Bogomolov, A. (2014). Determination of fat and total protein content in milk using conventional digital imaging. Talanta, 121, 144-152. https://doi.org/10.1016/j.talanta.2013.12.055

Vancouver

Kucheryavskiy S, Melenteva A, Bogomolov A. Determination of fat and total protein content in milk using conventional digital imaging. Talanta. 2014 Апр. 1;121:144-152. https://doi.org/10.1016/j.talanta.2013.12.055

Author

Kucheryavskiy, Sergey ; Melenteva, Anastasiia ; Bogomolov, Andrey. / Determination of fat and total protein content in milk using conventional digital imaging. в: Talanta. 2014 ; Том 121. стр. 144-152.

BibTeX

@article{813423e15e784cc3b0a3014f9e3cc669,
title = "Determination of fat and total protein content in milk using conventional digital imaging",
abstract = "The applicability of conventional digital imaging to quantitative determination of fat and total protein in cow's milk, based on the phenomenon of light scatter, has been proved. A new algorithm for extracting features from digital images of milk samples has been developed. The algorithm takes into account spatial distribution of light, diffusely transmitted through a sample. The proposed method has been tested on two sample sets prepared from industrial raw milk standards, with variable fat and protein content. Partial Least-Squares (PLS) regression on the features calculated from images of monochromatically illuminated milk samples resulted in models with high prediction performance when analysed the sets separately (best models with cross-validated R 2=0.974 for protein and R2=0.973 for fat content). However when analysed the sets jointly with the obtained results were significantly worse (best models with cross-validated R2=0.890 for fat content and R2=0.720 for protein content). The results have been compared with previously published Vis/SW-NIR spectroscopic study of similar samples.",
keywords = "Digital imaging, Image analysis, Light scatter, Milk quality",
author = "Sergey Kucheryavskiy and Anastasiia Melenteva and Andrey Bogomolov",
year = "2014",
month = apr,
day = "1",
doi = "10.1016/j.talanta.2013.12.055",
language = "English",
volume = "121",
pages = "144--152",
journal = "Talanta",
issn = "0039-9140",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Determination of fat and total protein content in milk using conventional digital imaging

AU - Kucheryavskiy, Sergey

AU - Melenteva, Anastasiia

AU - Bogomolov, Andrey

PY - 2014/4/1

Y1 - 2014/4/1

N2 - The applicability of conventional digital imaging to quantitative determination of fat and total protein in cow's milk, based on the phenomenon of light scatter, has been proved. A new algorithm for extracting features from digital images of milk samples has been developed. The algorithm takes into account spatial distribution of light, diffusely transmitted through a sample. The proposed method has been tested on two sample sets prepared from industrial raw milk standards, with variable fat and protein content. Partial Least-Squares (PLS) regression on the features calculated from images of monochromatically illuminated milk samples resulted in models with high prediction performance when analysed the sets separately (best models with cross-validated R 2=0.974 for protein and R2=0.973 for fat content). However when analysed the sets jointly with the obtained results were significantly worse (best models with cross-validated R2=0.890 for fat content and R2=0.720 for protein content). The results have been compared with previously published Vis/SW-NIR spectroscopic study of similar samples.

AB - The applicability of conventional digital imaging to quantitative determination of fat and total protein in cow's milk, based on the phenomenon of light scatter, has been proved. A new algorithm for extracting features from digital images of milk samples has been developed. The algorithm takes into account spatial distribution of light, diffusely transmitted through a sample. The proposed method has been tested on two sample sets prepared from industrial raw milk standards, with variable fat and protein content. Partial Least-Squares (PLS) regression on the features calculated from images of monochromatically illuminated milk samples resulted in models with high prediction performance when analysed the sets separately (best models with cross-validated R 2=0.974 for protein and R2=0.973 for fat content). However when analysed the sets jointly with the obtained results were significantly worse (best models with cross-validated R2=0.890 for fat content and R2=0.720 for protein content). The results have been compared with previously published Vis/SW-NIR spectroscopic study of similar samples.

KW - Digital imaging

KW - Image analysis

KW - Light scatter

KW - Milk quality

UR - http://www.scopus.com/inward/record.url?scp=84892885581&partnerID=8YFLogxK

U2 - 10.1016/j.talanta.2013.12.055

DO - 10.1016/j.talanta.2013.12.055

M3 - Article

C2 - 24607121

AN - SCOPUS:84892885581

VL - 121

SP - 144

EP - 152

JO - Talanta

JF - Talanta

SN - 0039-9140

ER -

ID: 41677780