Quameaty: Aplikasi Pendeteksi Kualitas Daging Ayam Mentah Berbasis Pengolahan Citra Menggunakan Model InceptionV3
DOI:
https://doi.org/10.31544/jtera.v7.i1.2022.107-114Keywords:
daging, pengolahan citra, jaringan saraf konvolusional, InceptionV3, AndroidAbstract
Dewasa ini, daging ayam telah menjadi sumber protein hewani yang baik untuk dikonsumsi dan mudah untuk didapatkan. Akan tetapi, dalam proses mendapatkannya seringkali ditemukan praktik curang, seperti daging ayam tiren yang tetap dijual, ataupun daging ayam yang telah dicampur dengan daging yang tidak layak jual. Maka dari itu, diperlukan sebuah alat atau aplikasi yang mampu mendeteksi kualitas daging ayam mentah. Tujuan penelitian ini untuk membuat alat yang berguna dalam mendeteksi kualitas daging ayam mentah dengan memanfaatkan pengolahan citra menggunakan model InceptionV3 dan diberi nama Quameaty. Alat ini dikembangkan menggunakan bahasa pemrograman Python. Model InceptionV3 merupakan model pelatihan jaringan saraf konvolusional yang sangat baik dan telah dilatih sebelumnya pada dataset Common Objects in Context (COCO) yang berjumlah 328 ribu gambar dengan 81 kelas yang berbeda. Model ini memiliki tingkat akurasi yang sangat tinggi sebagai pre-trained model dengan nilai top 5 accuracy sebesar 93,3% dan waktu komputasi yang relatif cepat apabila dibandingkan dengan model pendahulunya. Model pelatihan yang dihasilkan ditanam pada aplikasi Android yang mana dapat dengan mudah dan cenderung fleksibel untuk digunakan dalam mendeteksi kualitas daging ayam mentah. Hasil penelitian dibagi menjadi dua kelas yaitu segar dan busuk, serta menunjukkan bahwa prediksi kualitas daging ayam mentah berjalan dengan baik dengan nilai metrik pengujian yang telah mencapai lebih dari 90% pada dua nilai threshold, yaitu 50% dan 75%.
Downloads
References
J. de Macedo neto, J. dos Santos, and W. R. Schwartz, "Meat adulteration detection through digital image analysis of histological cuts using LBP," Federal University of Minas Grais, Belo Horizonte, 2016.
A. Ropodi, F. Mohareb, E. Panagou, and Pavlidis, "Multispectral image analysis approach to detect adulteration of beef and pork in raw meats," Food Research International, vol. 67, no. 1, pp. 12-18, 2015.
M. Al-Sarayreh, M. Reis, and W. Qi Yan, "Detection of Red-Meat Adulteration by Deep Spectral–Spatial Features in Hyperspectral Images," Journal of Imaging, vol. 4, no. 5, 2018.
H. Ayaz, A. Sohaib, M. Mazzara, and M. Ahmad, "Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features," Applied Sciences Journal, vol. 10, no. 1, pp. 1-13, 2020.
S. Agustin and R. Dijaya, "Beef Image Classification using K-Nearest Neighbor Algorithm for Identification Quality and Freshness," in Journal of Physics Conference Series, Tasikmalaya, 2018.
R. Jorfi, S. Mustafa, Y. Che Man, and D. Mat Hashim, "Differentiation of pork from beef, chicken, mutton and chevon according to their primary amino acids content for halal authentication," African Journal of Biotechnology, vol. 11, no. 32, pp. 8160-8166.
A. Wilson and Viancy, "Meat Monitoring System Using Machine Learning, Internet of Things," International Journal of Applied Engineering Research, vol. 14, no. 5, pp. 66-70, 2019.
E. F. Anggara, T. W. Widodo, and D. Lelono, "Deteksi Daging Sapi Menggunakan Electronic Nose Berbasis Bidirectional Associative Memory," IJEIS, vol. 7, no. 2, pp. 209-218, 2017.
Salsabila, A. Fitrianto, and B. Sartono, "Image Classification Modelling of Beef and Pork Using Convolutional Neural Network," International Journal of Sciences: basic and Applied research (IJSBAR), vol. 57, no. 2, pp. 26-38, 2021.
C. Szegedy, V. Vanhoucke, and S. Ioffe, "Rethinking the Inception Architecture for Computer Vision," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016.
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
The copyright to this article is transferred to JTERA if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to JTERA. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment. The copyright transfer form will be sent via email before the article published.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
