Evaluation of poultry meat colour using computer vision system and colourimeter Is there a difference?
Authorized Users Only
2019
Authors
Tomašević, IgorTomović, Vladimir
Ikonić, Predrag
Lorenzo Rodriguez, Jose Manuel
Barba, Francisco J.
Djekić, Ilija
Nastasijević, Ivan
Stajić, Slaviša
Živković, Dušan
Article (Published version)
Metadata
Show full item recordAbstract
Purpose -The purpose of this paper is to investigate the ability of the computer vision system (CVS) to evaluate the colour of poultry meat. The advantages of the CVS over traditional methods were also explored. Design/methodology/approach -The research was carried out on m. pectoralis major samples of three animals for each of the following four species: chicken, turkey, duck and goose. The total colour difference (.E) and the degree of difference of hue, chroma and lightness between the methods were calculated. In addition, a trained panel of 14 people was used to carry out three different similarity tests analysed using.2 one sample test and one-way ANOVA. The correlation coefficient between CVS and colourimeter measures was evaluated using the Spearman rank correlation test. Findings -The total colour difference (.E) between the methods employed was so large that the generated colour(s) could be considered more opposite than similar. The CVS-generated colour chips were more similar... to the sample of the meat products visualised on the monitor compared to colourimeter-generated colour chips in all (100 per cent) individual trials performed. The use of the colourimeter for colour evaluation of lighter coloured poultry meat (chicken and turkey) was unrepresentative. Practical implications - In this study, a CVS was developed to measure the colour of poultry meat as an alternative to conventional colourimeters. Originality/ value - The research has demonstrated that the use of a CVS should be considered a superior alternative to the traditional method for measuring colour of chicken, turkey, duck and goose meat.
Keywords:
Colour / Computer vision / Poultry meat / Image analysis / ColourimeterSource:
British Food Journal, 2019, 121, 5, 1078-1087Publisher:
- Emerald Group Publishing Ltd, Bingley
DOI: 10.1108/BFJ-06-2018-0376
ISSN: 0007-070X
WoS: 000483219200006
Scopus: 2-s2.0-85066948399
Collections
Institution/Community
Poljoprivredni fakultetTY - JOUR AU - Tomašević, Igor AU - Tomović, Vladimir AU - Ikonić, Predrag AU - Lorenzo Rodriguez, Jose Manuel AU - Barba, Francisco J. AU - Djekić, Ilija AU - Nastasijević, Ivan AU - Stajić, Slaviša AU - Živković, Dušan PY - 2019 UR - http://aspace.agrif.bg.ac.rs/handle/123456789/4957 AB - Purpose -The purpose of this paper is to investigate the ability of the computer vision system (CVS) to evaluate the colour of poultry meat. The advantages of the CVS over traditional methods were also explored. Design/methodology/approach -The research was carried out on m. pectoralis major samples of three animals for each of the following four species: chicken, turkey, duck and goose. The total colour difference (.E) and the degree of difference of hue, chroma and lightness between the methods were calculated. In addition, a trained panel of 14 people was used to carry out three different similarity tests analysed using.2 one sample test and one-way ANOVA. The correlation coefficient between CVS and colourimeter measures was evaluated using the Spearman rank correlation test. Findings -The total colour difference (.E) between the methods employed was so large that the generated colour(s) could be considered more opposite than similar. The CVS-generated colour chips were more similar to the sample of the meat products visualised on the monitor compared to colourimeter-generated colour chips in all (100 per cent) individual trials performed. The use of the colourimeter for colour evaluation of lighter coloured poultry meat (chicken and turkey) was unrepresentative. Practical implications - In this study, a CVS was developed to measure the colour of poultry meat as an alternative to conventional colourimeters. Originality/ value - The research has demonstrated that the use of a CVS should be considered a superior alternative to the traditional method for measuring colour of chicken, turkey, duck and goose meat. PB - Emerald Group Publishing Ltd, Bingley T2 - British Food Journal T1 - Evaluation of poultry meat colour using computer vision system and colourimeter Is there a difference? EP - 1087 IS - 5 SP - 1078 VL - 121 DO - 10.1108/BFJ-06-2018-0376 ER -
@article{ author = "Tomašević, Igor and Tomović, Vladimir and Ikonić, Predrag and Lorenzo Rodriguez, Jose Manuel and Barba, Francisco J. and Djekić, Ilija and Nastasijević, Ivan and Stajić, Slaviša and Živković, Dušan", year = "2019", abstract = "Purpose -The purpose of this paper is to investigate the ability of the computer vision system (CVS) to evaluate the colour of poultry meat. The advantages of the CVS over traditional methods were also explored. Design/methodology/approach -The research was carried out on m. pectoralis major samples of three animals for each of the following four species: chicken, turkey, duck and goose. The total colour difference (.E) and the degree of difference of hue, chroma and lightness between the methods were calculated. In addition, a trained panel of 14 people was used to carry out three different similarity tests analysed using.2 one sample test and one-way ANOVA. The correlation coefficient between CVS and colourimeter measures was evaluated using the Spearman rank correlation test. Findings -The total colour difference (.E) between the methods employed was so large that the generated colour(s) could be considered more opposite than similar. The CVS-generated colour chips were more similar to the sample of the meat products visualised on the monitor compared to colourimeter-generated colour chips in all (100 per cent) individual trials performed. The use of the colourimeter for colour evaluation of lighter coloured poultry meat (chicken and turkey) was unrepresentative. Practical implications - In this study, a CVS was developed to measure the colour of poultry meat as an alternative to conventional colourimeters. Originality/ value - The research has demonstrated that the use of a CVS should be considered a superior alternative to the traditional method for measuring colour of chicken, turkey, duck and goose meat.", publisher = "Emerald Group Publishing Ltd, Bingley", journal = "British Food Journal", title = "Evaluation of poultry meat colour using computer vision system and colourimeter Is there a difference?", pages = "1087-1078", number = "5", volume = "121", doi = "10.1108/BFJ-06-2018-0376" }
Tomašević, I., Tomović, V., Ikonić, P., Lorenzo Rodriguez, J. M., Barba, F. J., Djekić, I., Nastasijević, I., Stajić, S.,& Živković, D.. (2019). Evaluation of poultry meat colour using computer vision system and colourimeter Is there a difference?. in British Food Journal Emerald Group Publishing Ltd, Bingley., 121(5), 1078-1087. https://doi.org/10.1108/BFJ-06-2018-0376
Tomašević I, Tomović V, Ikonić P, Lorenzo Rodriguez JM, Barba FJ, Djekić I, Nastasijević I, Stajić S, Živković D. Evaluation of poultry meat colour using computer vision system and colourimeter Is there a difference?. in British Food Journal. 2019;121(5):1078-1087. doi:10.1108/BFJ-06-2018-0376 .
Tomašević, Igor, Tomović, Vladimir, Ikonić, Predrag, Lorenzo Rodriguez, Jose Manuel, Barba, Francisco J., Djekić, Ilija, Nastasijević, Ivan, Stajić, Slaviša, Živković, Dušan, "Evaluation of poultry meat colour using computer vision system and colourimeter Is there a difference?" in British Food Journal, 121, no. 5 (2019):1078-1087, https://doi.org/10.1108/BFJ-06-2018-0376 . .