DCT-based characterization of milk products using diffuse reflectance images

Sara Sharifzadeh, Jacob L. Skytte, Line H. Clemmensen, Bjarne K. Ersbøll

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

1 Citation (Scopus)

Abstract

We propose to use the two-dimensional Discrete Cosine Transform (DCT) for decomposition of diffuse reflectance images of laser illumination on milk products in different wavelengths. Based on the prior knowledge about the characteristics of the images, the initial feature vectors are formed at each wavelength. The low order DCT coefficients are used to quantify the optical properties. In addition, the entropy information of the higher order DCT coefficients is used to include the illumination interference effects near the incident point. The discrimination powers of the features are computed and used to do wavelength and feature selection. Using the selected features of just one band, we could characterize and discriminate eight different milk products. Comparing this result with the current characterization method based of a fitted log-log linear model, shows that the proposed method can discriminate milk from yogurt products better.
Original languageEnglish
Title of host publication2013 18th International Conference on Digital Signal Processing (DSP)
PublisherIEEE
Number of pages6
ISBN (Print)978-1-4673-5807-1
DOIs
Publication statusPublished - 1 Jul 2013
Externally publishedYes
Event18th International Conference on Digital Signal Processing (DSP) - Fira, Greece
Duration: 1 Jul 20133 Jul 2013
Conference number: 18

Conference

Conference18th International Conference on Digital Signal Processing (DSP)
CountryGreece
CityFira
Period1/07/133/07/13

Fingerprint

discrete cosine transform
milk
reflectance
products
illumination
wavelengths
coefficients
discrimination
entropy
interference
decomposition
optical properties
lasers

Keywords

  • Reflectivity
  • Dairy products
  • Optical reflection
  • Optical imaging

Cite this

Sharifzadeh, S., Skytte, J. L., Clemmensen, L. H., & Ersbøll, B. K. (2013). DCT-based characterization of milk products using diffuse reflectance images. In 2013 18th International Conference on Digital Signal Processing (DSP) IEEE. https://doi.org/10.1109/ICDSP.2013.6622669

DCT-based characterization of milk products using diffuse reflectance images. / Sharifzadeh, Sara; Skytte, Jacob L.; Clemmensen, Line H.; Ersbøll, Bjarne K.

2013 18th International Conference on Digital Signal Processing (DSP). IEEE, 2013.

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

Sharifzadeh, S, Skytte, JL, Clemmensen, LH & Ersbøll, BK 2013, DCT-based characterization of milk products using diffuse reflectance images. in 2013 18th International Conference on Digital Signal Processing (DSP). IEEE, 18th International Conference on Digital Signal Processing (DSP), Fira, Greece, 1/07/13. https://doi.org/10.1109/ICDSP.2013.6622669
Sharifzadeh S, Skytte JL, Clemmensen LH, Ersbøll BK. DCT-based characterization of milk products using diffuse reflectance images. In 2013 18th International Conference on Digital Signal Processing (DSP). IEEE. 2013 https://doi.org/10.1109/ICDSP.2013.6622669
Sharifzadeh, Sara ; Skytte, Jacob L. ; Clemmensen, Line H. ; Ersbøll, Bjarne K. / DCT-based characterization of milk products using diffuse reflectance images. 2013 18th International Conference on Digital Signal Processing (DSP). IEEE, 2013.
@inproceedings{e205ee015a11435489a78b88d12a5fa6,
title = "DCT-based characterization of milk products using diffuse reflectance images",
abstract = "We propose to use the two-dimensional Discrete Cosine Transform (DCT) for decomposition of diffuse reflectance images of laser illumination on milk products in different wavelengths. Based on the prior knowledge about the characteristics of the images, the initial feature vectors are formed at each wavelength. The low order DCT coefficients are used to quantify the optical properties. In addition, the entropy information of the higher order DCT coefficients is used to include the illumination interference effects near the incident point. The discrimination powers of the features are computed and used to do wavelength and feature selection. Using the selected features of just one band, we could characterize and discriminate eight different milk products. Comparing this result with the current characterization method based of a fitted log-log linear model, shows that the proposed method can discriminate milk from yogurt products better.",
keywords = "Reflectivity, Dairy products, Optical reflection, Optical imaging",
author = "Sara Sharifzadeh and Skytte, {Jacob L.} and Clemmensen, {Line H.} and Ersb{\o}ll, {Bjarne K.}",
year = "2013",
month = "7",
day = "1",
doi = "10.1109/ICDSP.2013.6622669",
language = "English",
isbn = "978-1-4673-5807-1",
booktitle = "2013 18th International Conference on Digital Signal Processing (DSP)",
publisher = "IEEE",

}

TY - GEN

T1 - DCT-based characterization of milk products using diffuse reflectance images

AU - Sharifzadeh, Sara

AU - Skytte, Jacob L.

AU - Clemmensen, Line H.

AU - Ersbøll, Bjarne K.

PY - 2013/7/1

Y1 - 2013/7/1

N2 - We propose to use the two-dimensional Discrete Cosine Transform (DCT) for decomposition of diffuse reflectance images of laser illumination on milk products in different wavelengths. Based on the prior knowledge about the characteristics of the images, the initial feature vectors are formed at each wavelength. The low order DCT coefficients are used to quantify the optical properties. In addition, the entropy information of the higher order DCT coefficients is used to include the illumination interference effects near the incident point. The discrimination powers of the features are computed and used to do wavelength and feature selection. Using the selected features of just one band, we could characterize and discriminate eight different milk products. Comparing this result with the current characterization method based of a fitted log-log linear model, shows that the proposed method can discriminate milk from yogurt products better.

AB - We propose to use the two-dimensional Discrete Cosine Transform (DCT) for decomposition of diffuse reflectance images of laser illumination on milk products in different wavelengths. Based on the prior knowledge about the characteristics of the images, the initial feature vectors are formed at each wavelength. The low order DCT coefficients are used to quantify the optical properties. In addition, the entropy information of the higher order DCT coefficients is used to include the illumination interference effects near the incident point. The discrimination powers of the features are computed and used to do wavelength and feature selection. Using the selected features of just one band, we could characterize and discriminate eight different milk products. Comparing this result with the current characterization method based of a fitted log-log linear model, shows that the proposed method can discriminate milk from yogurt products better.

KW - Reflectivity

KW - Dairy products

KW - Optical reflection

KW - Optical imaging

U2 - 10.1109/ICDSP.2013.6622669

DO - 10.1109/ICDSP.2013.6622669

M3 - Conference proceeding

SN - 978-1-4673-5807-1

BT - 2013 18th International Conference on Digital Signal Processing (DSP)

PB - IEEE

ER -