Keywords
color sensor
Arduino microcontroller
automated system
RGB color components
mechanical sorting
artificial intelligence
real-time processing
How to Cite
Abstract
This paper presents the development of an automatic fruit sorting system based on color characteristics using an Arduino microcontroller and a TCS230 color sensor. The proposed system is designed to detect external color features of fruits in real time, process RGB color components, and classify fruits according to predefined criteria. The study focuses on automating quality assessment processes in agricultural and food production sectors.
The system operation algorithm includes color data acquisition, object detection using infrared sensors, and control of a mechanical sorting mechanism. Sensor calibration was applied to reduce the influence of external lighting conditions and improve color detection accuracy. Experimental results demonstrated stable system performance and reliable color-based fruit classification.
In addition, the paper discusses the potential integration of artificial intelligence techniques, particularly neural networks, to enhance sorting accuracy. Compared to conventional threshold-based methods, intelligent approaches allow more precise discrimination of subtle color differences. The obtained results indicate that the proposed system is a promising solution for improving efficiency and reliability in automatic fruit sorting applications.
References
[1] Blasco J., Cubero S., Moltó E. Vision-based quality inspection of fruits and vegetables. Biosystems Engineering, 2018, 176, pp. 97–108.
[2] Uljaev E., Abdixalilov U., Suleymanova S., Tadjitdinov G.
Analysis of Methods and Means of Fruit Sorting, Selection of a Rational Method of Fruit Sorting.
International Journal of Mechatronics and Applied Mechanics, 2025, Issue 22, Vol. II, pp. 233–241.
[3] Patel K.K., Kar A., Jha S.N., Khan M.A. Machine vision system: a tool for quality inspection of food and agricultural products. Journal of Food Science and Technology, 2018, 55(6), pp. 1974–1989.
[4] Uljaev E., Abdixalilov O‘.U. Sun’iy intellekt asosida meva saralash tizimlarini takomillashtirish: mexanik va optik usullar tahlili. The Role and Prospects of Modeling in the Processes of Digital Transformation: Xalqaro ilmiy va ilmiy-texnik konferensiya materiallari, 1-qism, Namangan: Namangan davlat texnika universiteti, 2025, 4–5-dekabr.
[5] Kumar S., Singh R. Arduino-based low-cost color sensing system for agricultural applications. IEEE Sensors Journal, 2020, 20(12), pp. 6789–6796.
[6] Perez-Borrero I., et al. Fruit quality assessment using color and vision-based systems. Computers and Electronics in Agriculture, 2020, 175, 105–118.
[7] Li J., Rao X., Ying Y. Calibration methods for color sensors in agricultural product grading. Sensors, 2021, 21(8), 2674.
[8] Kamilaris A., Prenafeta-Boldú F.X. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 2018, 147, pp. 70–90.
[9] Mohanty S.P., Hughes D.P., Salathé M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 2019, 10, 272.
[10] G‘ayimnazarov I. X. UDC 532.543: 627.157: Calculation of the parameters of the base rows in a non-stationary flow //Innovatsion texnologiyalar. – 2025. – Т. 59. – №. 3. – С. 62-66.
[11] Lu Y., Yi S., Zeng N. Identification of fruit ripeness based on color features and machine learning. Measurement, 2022, 187, 110–118.
[12] Gonzales R. C., Woods R. E. Digital Image Processing. 4th ed., Pearson Education, New York, 2018.
[13] Jayaraman S., Esakkirajan S., Veerakumar T. Digital Image Processing. Tata McGraw-Hill Education, New Delhi, 2011.
[14] Haykin S. Neural Networks and Learning Machines. 3rd ed., Pearson Education, New York, 2009.
[15] Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, Cambridge, 2016.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Uljaev E., Abdixalilov O‘.U. (Muallif)