Computational method for color vision of coffee bean roasting using openCV

Authors

  • ชัยณรงค์ วิเศษศักดิ์วิชัย Faculty of Engineering, Rajamangala University of Technology Krungthep
  • ประเสริฐ เผ่าชู Faculty of Science and Technology, Rajamangala University of Technology Krungthep
  • เอกพล อนุสุเรนทร์ Faculty of Engineering, Rajamangala University of Technology Krungthep
  • ชูศักยฐ์ กมลขันติธร Faculty of Engineering, Rajamangala University of Technology Krungthep
  • วินัย เมธาวิทิต Faculty of Engineering, Rajamangala University of Technology Krungthep

Keywords:

Computer vision, Digital image processing, Programmatic object, HSV color space, Histogram equalization, Probability distribution, Expected value, Random variables

Abstract

Development of software for computer vision system which does not depend upon computer platforms can be accomplished by appropriate programming language. This paper presents the computational method for color vision of coffee bean roasting using the open source of C++ programing language. Digital image processing is performed on the image file recording in secondary memory unit of computer system. The programmatic object of image file is created by the library of OpenCV (open source computer vision) using HSV (hue-saturation-value) color space where the color channels separate into the instances of object-oriented programming. The histogram equalization operates on selected instance for intensity stretching before all of them are modeled with discrete probability distribution of color intensity in red green and blue. The numerical color representations of roast coffee beans are determined by expected values and standard deviation of random variables. The developed program can execute in both personal computer and Raspberry Pi computer single board with Widows and Linux operating system respectively.

Author Biography

เอกพล อนุสุเรนทร์, Faculty of Engineering, Rajamangala University of Technology Krungthep

Development of software for computer vision system which does not depend upon computer platforms can be accomplished by appropriate programming language. This paper presents the computational method for color vision of coffee bean roasting using the open source of C++ programing language. Digital image processing is performed on the image file recording in secondary memory unit of computer system. The programmatic object of image file is created by the library of OpenCV (open source computer vision) using HSV (hue-saturation-value) color space where the color channels separate into the instances of object-oriented programming. The histogram equalization operates on selected instance for intensity stretching before all of them are modeled with discrete probability distribution of color intensity in red green and blue. The numerical color representations of roast coffee beans are determined by expected values and standard deviation of random variables. The developed program can execute in both personal computer and Raspberry Pi computer single board with Widows and Linux operating system respectively.

References

[1] Andhare P, Rawat SP. Pick and Place Industrial Robot Controller with Com puter Vision. 2016 International Conference on Computing Commu nication Control and automation (ICCUBEA); 2016 Aug 12-13; Pune, India: IEEE; 2016:1-4.

[2] Mery D, Pedreschi F, Soto A. Automated Design of a Computer Vision System for Visual Food Quality Evaluation. Food and Bioprocess Technology, 2013; 6(8): 2093-2108.

[3] Priyadharshini K, Akila R. A Survey on Computer Vision Technology for Food Quality Evaluation. IJIRCCE 2016; 4(8): 14860–65.

[4] Habib MT, Majumder A, Jakaria AZM, et al. Machine Vision Based Papaya Disease Recognition. Journal of King Saud Uni versity-Computer and Infor mation Sciences, 2018.

[5] Trientin D, Hidayat B, Darana S. Beef Freshness Classification by Using Color Analysis, Multi-wavelet Transformation and Artificial Neural Network. 2015 International Conference on Automa tion, Cognitive Science, Optics, Micro Electro-Mechanical System, and Infor mation Technology (ICACOMIT); 2015 Oct 29-30; Bandung, Indonesia: IEEE; 2015:181-85.

[6] Adi K, Pujiyanto S, Nurhayati OD, et al. Beef Quality Identifica tion Using Color Analysis and K-nearest Neighbor Classification. 2015 4th International Conference on Instrumen tation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME); 2015 Nov 2-3; Bandung, Indonesia: IEEE; 2015:180-4.

[7] Laurent B, Ousman B, Dzudie T,et al. Digital Camera Images Processing of Hard-to-Cook Beans. J Eng Tech Res, 2010; 2(9): 177 – 88.

[8] Garcia G, Suarez OD, Aranda JLE, et al. Learning Image Processing with Open CV. Birmingham: Packt Publishing Ltd; 2015

[9] Burger W, Burge MJ. Principles of Digital Image Processing: Fundamental Techniques. London: Springer-Verlag London Limited; 2009.

[10] Rao S. The Coffee Roaster's Compa nion. Canada: Scott Rao; 2014.

[11] Kaehler A, Bradski G. Learning OpenCV 3: Computer Vision in C++ with The OpenCV library. Tokyo: O'Reilly Media, Inc.; 2017.

[12] Gonzalez RC, Woods RE. Digital Image Processing. New Jersey: Prentice Hall; 2002.

[13] Sinnott K. The Art and Craft of Coffee: An Enthusiast's Guide to Selecting, Roasting, and Brewing Exquisite Coffee. Massachusetts: Quarry Books; 2011.

Downloads

Published

2019-12-11

How to Cite

[1]
วิเศษศักดิ์วิชัย ช., เผ่าชู ป., อนุสุเรนทร์ เ., กมลขันติธร ช., and เมธาวิทิต ว., “Computational method for color vision of coffee bean roasting using openCV”, UTK RESEARCH JOURNAL, vol. 13, no. 2, pp. 25–38, Dec. 2019.

Issue

Section

Research Articles