Effect of number of colors and order of priority components on quality evaluation of white cheese in brine using images segmentation with SegPC algorithm Effect of number of colors and order of priority components on…
Article Sidebar
Main Article Content
Abstract
In the last decade, there has been a growing interest in the field of application methods of computer vision for cheese quality evaluation and Bulgarian WCB (white cheese in brine) is also an object of research in this direction. Certain quality indicators of WCB are successfully evaluated using image processing based on thresholding and multi-level thresholding algorithms. The current study aims to examine one novel algorithm for image segmentation (named SegPC) for its effectiveness in the quality evaluation of WCB. A database of images that present the structure of WCB is used for this research. A software with GUI (Graphical User Interface) is developed for easy usage of the SegPC algorithm and images of eight trademarks of WCB are processed using different settings for the algorithm’s two parameters (number of colors and priority of color components). All segmented images are used for analysis using PSNR (Peak Signal to Noise Ratio) metric. Statistical information about the distribution of pixels in segmented images is used for comparison with experts’ assessment for the quality of cheese structure. The best matching results are a basis for further analysis to build a regression model. The settings of experiments are values from 2 to 10 for the number of colors parameter and all possible permutations for the order of priority components parameter. Regarding calculated PSNR values it could be concluded that at least four colors are necessary for segmentation to preserve more details in images and thus significant information about cheese structure to be extracted. The highest correlation coefficient that is achieved is 0.88 which indicates a very strong relationship. The results indicate that the number of colors influences significantly on the quality of the segmented images and consequently, influences the process of information extraction, the order of priority components has to be preciously selected based on specifics of the input images, and PSNR metric allows better understanding the segmentation results.
Article Details
References
Bosakova-Ardenska A., Panayotov P., Boyanova P., Pashova E. Application of images segmentation for evaluation structure of white brined cheese. IEEE Xplore, 2020, International Conference on Information Technologies InfoTech(10): 9211039. https://doi.org/10.1109/InfoTech49733.2020.9211039
Bosakova-Ardenska A., Danev A. An algorithm for histogram median thresholding. ACM International Conference Proceeding Series, 2018, CompSysTech '18: Proceedings of the 19th International Conference on Computer Systems and Technologies (9): 62-67. https://doi.org/10.1145/3274005.3274019
Bosakova-Ardenska A., Kutryanska M., Boyanova P., Panayotov P. Cheese quality evaluation using images smoothing and algorithm for statistical region merging. AIP Conference Proceedings, 2023, 2889(1): 010001. https://doi.org/1 10.1063/5.0173120
Bosakova-Ardenska A., Kutryanska M., Boyanova P., Panayotov P. Application of images segmentation and median filter for white brined cheese structure evaluation. AIP Conference Proceedings, 2022, 2570(1): 020014. https://doi.org/10.1063/5.0099673
Caccamo M., Melilli C., Barbano D.M., Portelli G., Marino G., Licitra G. Measurement of gas holes and mechanical openness in cheese by image analysis. Journal of Dairy Science, 2004, 87(3): 739-748. https://doi.org/10.3168/jds.S0022-0302(04)73217-8
Cerruto E., Manetto G., Privitera S., Papa R., Longo D. Effect of image segmentation thresholding on droplet size measurement. Agronomy, 2022, 12(7): 12071677. https://doi.org/10.3390/agronomy12071677
Danev A., Bosakova-Ardenska A., Boyanova P., Panayotov P., Kostadinova-Georgieva L. Cheese quality evaluation by image segmentation. CompSysTech '19: Proceedings of the 20th International Conference on Computer Systems and Technologies, 2019, 2019(6): 161-168. https://doi.org/10.1145/3345252.3345258
Danev A., Gabrova R., Yaneva-Marinova T., Angelov A. Application possibilities of open-source software for microbiological analyses. Bulgarian Chemical Communications, 2018, 50(Special Issue G): 239-245. Available at: http://www.bcc.bas.bg/BCC_Volumes/Volume_50_Special_G_2018/50G_PD_239-245.147.pdf
Fardo F., Conforto V., De Oliveira F., Rodrigues P. A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms. Accessibility Forum 2024 (arXiv:1605.07116v1 [cs.CV]), 2016, 1(5): 07116. https://doi.org/10.48550/arXiv.1605.07116
Gmurman V.E. Probability Theory and Mathematical Statistics. (10th Edition). Moscow: Higher School, 2004, ISBN: 5-06-004214-6. [in Russian]
Gonzalez R.C., Woods R.E. Digital Image Processing (4th Edition). In: Pearson Education (R.C. Gonzalez, R.E. Woods Eds.). Pearson Global Editions, 2018, 1022 pages. Available at: https://dl.icdst.org/pdfs/files4/01c56e081202b62bd7d3b4f8545775fb.pdf
Houssein E.H., Mohamed G.M., Ibrahim I.A., Wazery Y.M. An efficient multilevel image thresholding method based on improved heap-based optimizer. Scientific Reports, 2023, 13(1): 9094. https://doi.org/10.1038/s41598-023-36066-8
Hussain A.J., Al-Fayadh A., Radi N. Image compression techniques: A survey in lossless and lossy algorithms. Neurocomputing, 2018, 300(7): 44-69. https://doi.org/10.1016/j.neucom.2018.02.094
Illa I., Chan T., Fadzli R., Safwati I., Rosmaini A., Fathullah M. Product defect prediction model in food manufacturing production line using multiple regression analysis (MLR). AIP Conference Proceedings, 2021, 2347(1): 020241. https://doi.org/10.1063/5.0052688
Impoco G., Fucà N., Tuminello L., Licitra G., Quantitative image analysis of food microstructure. Current microscopy contributions to advances in science and technology, 2012, 2: 903-911. Available at: https://d1wqtxts1xzle7.cloudfront.net/101293433/903-911-libre.pdf?1681984683=&response-content-disposition=inline%3B+filename%3DQuantitative_image_analysis_of_food_micr.pdf&Expires=1726044476&Signature=a6BJZv2NLKuqmDx822Jv-adhKGGWbEmsu-KNkHtvWlanIaSFNmTOXPnVyUvnipFjM0h49-4HR8AN1VeJZt4ZJpDzLu8AyjlOv7nrruJSf38RbA0h4rgpVAcNCY~c1Idfifzn3dgBk4PB3P97EDPKatauvXmNRooTu~wmY8VMyLzPdYXfVODpsmFsiRn7YcQv0XgU8fB6nMXDi587uR6A4YwL-4yHYRX~SE1~htaerzVnpUSXgwK~dTgCIDts-gNO1RGbRPtFk6xUDKNerHRTyUuHImmMBEesxSK3qjvvgcfvieJHuimtVe-P2p27R7AbBdQFSYvECBFYkdz3X3SHRg__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA
Ivanov G.Y., Bilgücü E., Balabanova T.G., Ivanova I.V. Effect of somatic cell count of cow’s milk on the lipolysis and fatty acid profile of farmer cheese. International Food Research Journal, 2021, 28(6): 1171-1178. https://doi.org/10.47836/ifrj.28.6.08
Jardim S., António J., Mora C. Image thresholding approaches for medical image segmentation - short literature review. Procedia Computer Science, 2023, 219(1): 1485-1492. ISSN: 1877-0509. https://doi.org/10.1016/j.procs.2023.01.439
Jeliński T., Du C., Sun D., Fornal J. Inspection of the distribution and amount of ingredients in pasteurized cheese by computer vision. Journal of Food Engineering, 2007, 83(1): 3-9. https://doi.org/10.1016/j.jfoodeng.2006.12.020
Liao P.S., Chen T.S., Chung P.C. A fast algorithm for multilevel thresholding, Journal of Information Science and Engineering, 2001, 17(5): 713-727. Available at: http://smile.ee.ncku.edu.tw/old/Links/MTable/ResearchPaper/papers/2001/A%20fast%20algorithm%20for%20multilevel%20%20thresholding.pdf
Liu W., Guo A., Bao X., Li Q., Liu L., Zhang X., Chen X., Statistics and analyses of food safety inspection data and mining early warning information based on chemical hazards. LWT, 2022, 165(8): 113746. https://doi.org/10.1016/j.lwt.2022.113746
Mathews S. Interpreting Regression Output (Without All the Statistics Theory). Graduatetutor Official Portal. 2018, GraduateTutor.com. Available at: https://www.graduatetutor.com/statistics-tutor/interpreting-regression-output/
Nock R., Nielsen F. Statistical region merging. IEEE Xplore, 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11): 1452-1458. https://doi.org/10.1109/TPAMI.2004.110
Ostovar A., Ringdahl O., Hellström T. Adaptive image thresholding of yellow peppers for a harvesting robot. Robotics, 2018, 7(1): 11. https://doi.org/10.3390/robotics7010011
Pilevar A.H., Saien S., Khandel M., Mansoori B. A new filter to remove salt and pepper noise in color images. Signal, Image and Video Processing, 2015, 9(4): 779-786. https://doi.org/10.1007/s11760-013-0514-6
Sara U., Akter M., Uddin M. Image quality assessment through FSIM, SSIM, MSE and PSNR – A comparative study. Journal of Computer and Communications, 2019, 7(3): 8-18. https://doi.org/10.4236/jcc.2019.73002
Schindelin J., Arganda-Carreras I., Frise E. Fiji: an open-source platform for biological-image analysis. Nature Methods, 2012, 9(6): 676-682. https://doi.org/10.1038/nmeth.2019
Sezgin M., Sankur B. Survey over image thresholding techniques and quantitative performance evaluation, Journal of Electronic Imaging, 2004, 13(1): 146-165. https://doi.org/10.1117/1.1631315
Shi X., Misch D., Vranjes-Wessely S. A comprehensive assessment of image processing variability in pore structural investigations: Conventional thresholding vs. machine learning approaches. Gas Science and Engineering, 2023, 115(7): 205022. https://doi.org/10.1016/j.jgsce.2023.205022
Teneva-Angelova T., Balabanova T., Boyanova P., Beshkova D. Traditional Balkan fermented milk products. Engineering in Life Sciences, 2018, 18: 807-819. https://doi.org/10.1002/elsc.201800050
van Eijnatten M., Koivisto J., Karhu K., Forouzanfar T., Wolff J. The impact of manual threshold selection in medical additive manufacturing. International Journal of Computer Assisted Radiology and Surgery, 2017, 12(10): 607-615. https://doi.org/10.1007/s11548-016-1490-4
Wu Q., Fang Z., Song Z., Chen H., Lu Y., Zhou L., Qian X. A color extraction algorithm by segmentation. Scientific Reports, 2023, 13(2): 21261. https://doi.org/10.1038/s41598-023-48689-y
Yu Y., Wang C., Fu Q., Kou R., Huang F., Yang B., Yang T., Gao M. Techniques and challenges of image segmentation: a review. Electronics, 2023, 12(5): 1199. https://doi.org/10.3390/electronics12051199
Zuodong N., Handong L. Research and analysis of threshold segmentation algorithms in image processing. Journal of Physics: Conference Series, 2019, 1237(2): 022122. https://doi.org/10.1088/1742-6596/1237/2/022122
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Open access articles are distributed under the terms and conditions of the Creative Commons Attribution-Share Alike 4.0 International License (CC BY-SA 4.0) license:
https://creativecommons.org/licenses/by-sa/4.0
If you have any questions about the permitted uses of a specific article, please contact us.
Permissions Department of the Academic Publishing House of the UFT Plovdiv
Plovdiv 4002, 26 Maritsa Blvd., Bulgaria
E-mail: editor.in.chief@ijfsab.com
Tel.: +359 (32) 603-802
Fax: +359 32/ 644 102