Classification of Rice Quality Using Backpropagation Based on Shape and Color

Authors

  • Olief Ilmandira Ratu Farisi Universitas Nurul Jadid
  • Gulpi Qorik Oktagalu Pratamasunu Universitas Nurul Jadid
  • Siti Sulaihah Universitas Nurul Jadid

DOI:

https://doi.org/10.21111/fij.v7i2.7594

Keywords:

rice quality, classification, backpropagation, shape feature, color feature

Abstract

AbstractThe distribution of mixed rice on the market makes it difficult for consumers to determine the rice quality. In determining rice quality, the consumers consider and compare the texture, size, shape, color, aroma, purity, and homogeneity manually. This process is prone to errors and mistakes, due to the limited ability of each human's vision. Therefore, a method to determine the quality of rice automatically based on the physical characteristics of rice is needed. In this paper, we proposed an automatic rice quality classification method using backpropagation based on the shape and color of the rice. There are four parameters used to determine the classification process, namely compactness, circularity, mean, and skewness. Compactness and circularity were used to determine the ratio between the whole rice and the broken rice. While mean and skewness were used to determine the color distribution of the rice. Experiments have been performed on 100 images consisting of 50 premium and 50 medium rice images. The experimental results show that the proposed method can classify rice based on its shape and color effectively with an accuracy rate of 95%.Keywords: rice quality, classification, backpropagation, shape feature, color feature Abstrak[Klasifikasi Kualitas Beras Menggunakan Backpropagation Berdasarkan Bentuk dan Warna] Distribusi beras oplosan di pasaran menyulitkan konsumen dalam menentukan kualitas beras. Konsumen mempertimbangkan dan membandingkan tekstur, ukuran dan bentuk, warna, aroma, kemurnian, dan keseragaman secara manual untuk menentukan kualitas beras. Proses ini rawan terjadi kesalahan dan kekeliruan, karena keterbatasan kemampuan penglihatan setiap manusia. Oleh karena itu diperlukan suatu metode untuk menentukan kualitas beras secara otomatis berdasarkan karakteristik fisik beras. Dalam penelitian ini, kami mengusulkan metode klasifikasi kualitas beras otomatis menggunakan backpropagation berdasarkan bentuk dan warna beras. Ada empat parameter yang digunakan untuk menentukan proses klasifikasi yaitu compactness, circularity, mean, dan skewness. Compactness dan circularity digunakan untuk menentukan perbandingan antara nasi utuh dan nasi pecah. Sedangkan mean dan skewness digunakan untuk menentukan distribusi warna beras. Percobaan telah dilakukan pada 100 citra yang terdiri dari 50 citra beras premium dan 50 citra beras medium. Hasil percobaan menunjukkan bahwa metode yang diusulkan dapat mengklasifikasikan beras berdasarkan bentuk dan warnanya secara efektif dengan tingkat akurasi 95%.Kata kunci: kualitas beras, klasifikasi, backpropagation, fitur bentuk, fitur warna

References

[1] D. D. Handoko, “Seputar Mutu Beras Kemasan dan Pencampuran Beras,” Ministry of Agriculture Republic Indonesia. https://www.pertanian.go.id/home/?show=news&act=view&id=2129 (accessed Jul. 26, 2021).[2] M. C. Custodio, R. P. Cuevas, J. Ynion, A. G. Laborte, M. L. Velasco, and M. Demont, “Rice quality: How is it defined by consumers, industry, food scientists, and geneticists?,” Trends Food Sci. Technol., vol. 92, pp. 122–137, Oct. 2019, doi: 10.1016/J.TIFS.2019.07.039.[3] N. Hong Son and N. Thai-Nghe, “Deep Learning for Rice Quality Classification,” Proc. - 2019 Int. Conf. Adv. Comput. Appl. ACOMP 2019, pp. 92–96, Nov. 2019, doi: 10.1109/ACOMP.2019.00021.[4] F. N. Fajri, N. Hamid, and R. A. Pramunendar, “The recognition of mango varieties based on the leaves shape and texture using back propagation neural network method,” Proc. - 2017 Int. Conf. Sustain. Inf. Eng. Technol. SIET 2017, vol. 2018-January, pp. 14–20, Feb. 2018, doi: 10.1109/SIET.2017.8304101.[5] BSN, SNI 6128:2015 Uji Mutu Beras. Jakarta: Badan Standardisasi Nasional, 2015.[6] G. Kumar and P. K. Bhatia, “A detailed review of feature extraction in image processing systems,” Int. Conf. Adv. Comput. Commun. Technol. ACCT, pp. 5–12, 2014, doi: 10.1109/ACCT.2014.74.[7] W. K. Mutlag, S. K. Ali, Z. M. Aydam, and B. H. Taher, “Feature Extraction Methods: A Review,” J. Phys. Conf. Ser., vol. 1591, no. 1, p. 012028, Jul. 2020, doi: 10.1088/1742-6596/1591/1/012028.[8] M. Ravichandran, D., Nimmatoori, R., Ashwin Dhivakar, “A study on Image Statistics and Image Features on Coding Performance of Medical Images,” Int. J. Adv. Comput. Eng. Commun. Technol., vol. 5, no. 1, pp. 1–6, 2016.[9] F. D. Syahfitra, R. Syahputra, and K. T. Putra, “Implementation of Backpropagation Artificial Neural Network as a Forecasting System of Power Transformer Peak Load at Bumiayu Substation,” J. Electr. Technol. UMY, vol. 1, no. 3, pp. 118–125, Dec. 2017, doi: 10.18196/JET.1316.[10] M. Athoillah, M. I. Irawan, and E. M. Imah, “STUDY COMPARISON OF SVM-, K-NN- AND BACKPROPAGATION-BASED CLASSIFIER FOR IMAGE RETRIEVAL,” J. Ilmu Komput. dan Inf., vol. 8, no. 1, pp. 11–18, Mar. 2015, doi: 10.21609/JIKI.V8I1.279.

Downloads

Submitted

2022-03-22

Accepted

2022-06-27

Published

2024-02-13

Issue

Section

Articles