STM Journals Peer-reviewed research from Consortium e-Learning Network

International Journal of Biomedical Innovations and Engineering Original Research

Fruit Adulteration Detection Utilizing Machine Learning Methods

  1. Khallikkunaisa Department of Computer Science and Engineering, Visveswaraya Technological University
  2. Shivani S Department of Computer Science and Engineering, Visveswaraya Technological University
  3. Spandana V Department of Computer Science and Engineering, Visveswaraya Technological University
  4. Sudhiksha S Department of Computer Science and Engineering, Visveswaraya Technological University
  5. Vidhya K.C Department of Computer Science and Engineering, Visveswaraya Technological University

Abstract

A device utilizing Internet of Things (IoT) technology was developed for the identification of fruit adulteration through machine learning methods, specifically targeting formalin content assessment. The identification of the fruits based on their extracted traits has been accomplished using a variety of machine-learning techniques. The formalin concentration can be detected as an estimate of the generated voltage of any fruit via an Arduino Uno board 3 and a volatile compound sensor. The approach we use can distinguish between organically formed and chemically added formalin utilizing machine learning methods that precisely predict the ideal formalin content at any temperature. The primary aim of this system is to supplant traditional inspection approaches. This approach involves capturing images using cameras installed on moving belt conveyors. By analyzing the picture pixels, key characteristics of fruits are used to detect contaminated ones. Subsequently, the fruits are sorted based on their size and color.

Keywords

References (10)

  1. Kaur S, Girdhar A, Gill J. Computer Vision-Based Tomato Grading and Sorting. Lecture Notes in Networks and Systems. 2018:75-84. doi:10.1007/978-981-10-8360-0_7
  2. Sharma D, Sawant SD. Grain quality detection by using image processing for public distribution. 2017 International Conference on Intelligent Computing and Control Systems (ICICCS). 2017:1118-1122. doi:10.1109/iccons.2017.8250640
  3. Parveen Z, Alam MA, Shakir H. Assessment of quality of rice grain using optical and image processing technique. 2017 International Conference on Communication, Computing and Digital Systems (C-CODE); 2017 March 8-9; Islamabad, Pakistan. IEEE; 2017. p. 265–270. doi:10.1109/CCODE.2017.7918940.
  4. Satpute MR, Jagdale SM. Automatic fruit quality inspection system. 2016 International Conference on Inventive Computation Technologies (ICICT). 2016:1-4. doi:10.1109/inventive.2016.7823207
  5. Nandi CS, Tudu B, Koley C. Machine Vision Based Techniques for Automatic Mango Fruit Sorting and Grading Based on Maturity Level and Size. Smart Sensors, Measurement and Instrumentation. 2013:27-46. doi:10.1007/978-3-319-02315-1_2
  6. Patil SV, Jadhav VM, Dalvi KK, Kulkarni BP. Fruit quality detection using OpenCV/Python. Int Res J Eng Technol. 2020 May;7(5):6658–60.
  7. Nandhini P, Jaya J, George J. Computer vision system for food quality evaluation — A review. 2013 International Conference on Current Trends in Engineering and Technology (ICCTET). 2013:85-87. doi:10.1109/icctet.2013.6675916
  8. Cortez C. Development of Formaldehyde Detector. International Journal of Information and Electronics Engineering. 2015. doi:10.7763/ijiee.2015.v5.564
  9. East West University, Dhaka, Bangladesh, Tabassum K, Memi AA, Sultana N, Reza AW, Barman SD. Food and Formalin Detector Using Machine Learning Approach. International Journal of Machine Learning and Computing. 2019;9(5):609-614. doi:10.18178/ijmlc.2019.9.5.847
  10. Woo Chaw Seng, Mirisaee SH. A new method for fruits recognition system. 2009 International Conference on Electrical Engineering and Informatics. 2009:130-134. doi:10.1109/iceei.2009.5254804