Penerapan SSD-Mobilenet Dalam Identitas Jenis Buah Apel

Zulfahmi Syahputra

doi:10.60076/indotech.v1i1.2

Authors

Zulfahmi Syahputra Universitas Pembangunan Panca Budi

DOI:

https://doi.org/10.60076/indotech.v1i1.2

Keywords:

SSD-Mobilenet, Identification, Apple

Abstract

Under conditions that determine whether an apple is good or not, the human eye tends to have a subjective perception due to the color composition factor. Errors often occur because it is done manually. Therefore we need a tool with a system that can choose apples automatically based on their type. So we need a system that can identify the ripeness of apples by implementing SSD-Mobilenet. The purpose of this research is to identify the types of apples using SSD-MobileNet. From the results of the analysis and testing it can be concluded that the test results on data testing with lots of data, namely 50 datasets taken randomly produce an accuracy of 82% and an error of 18%. The number of errors indicates that the classification results are not completely accurate. This can happen due to the lack of training data so that only a few dominant terms are used, causing errors in course costs. However, the results of this accuracy can be used as a reference that assistance using SSD-Mobilenet provides a high value of 82%. So this method can be used to analyze the ripeness of apples.

Downloads

Download data is not yet available.

References

Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Andreetto, M., & Adam, H. 2017, MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861.

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S. Yang Fu, C., Breg A, C. 2016. SSD: Single Shot MultiBox Detector. arXiv:1512.02325

Al-Azzo, F, Taqi. M. A, And Milanova. "Human Related-Health Actions Detection Using Android Camera Based On Tensorflow Object Detection Api," International Journal Of Advanced Computer Science And Applications (Ijacsa) , Vol. 09, No. 10, Pp. 9-23, 2018.

Arabi, S., Haghighat, A., & Sharma, A. (2019). A deep learning based solution for construction equipment detection: from development to deployment. arXiv preprint arXiv:1904.09021.

Avif, B, A. (2019). Klasifikasi Tanaman Herbal Zingiber Berdasarkan Citra Mikroskopis Stomata Menggunakan Algoritma Probabilistic Neural Network (PNN). Universitas Sumatera Utara.

Biswas, D., Su, H., Wang, C., Stevanovic, A., & Wang, W. (2019). An automatic traffic density estimation using Single Shot Detection (SSD) and MobileNet-SSD. Physics and Chemistry of the Earth, 110, 176–184.

Ichsan, A, F. (2021) Implementasi relevance vector machine untuk mengidentifikasi penyakit mata glaukoma. Skripsi, Institut Teknologi Nasional.

Kanimozhi, S., Gayathri, G., & Mala, T. (2019). Multiple object identification using single shot multi-box detection. ICCIDS 2019 - 2nd International Conference on Computational Intelligence in Data Science, Proceedings, 1–5.

Sufrida dan Maloedyn S. 2006. 30 Ramuan Penakluk Hipertensi. Edisi 1. Jakarta: Agromedia Pustaka.

Suhardjo, H. L., Deaton, B. J., & Driskel, J. A. (1985). Pangan, Gizi dan Pertanian. UI-Pers Jakarta.

Soelarso, Bambang. 1997. Budidaya Apel. Yogyakarta: Penerbit Kanisius (Anggota IKAPI).

Syahputra, Z. (2020) “Website Based Sales Information System With The Concept Of Mvc (Model View Controller): Website Based Sales Information System With The Concept Of Mvc (Model View Controller)”, Jurnal Mantik, 4(2), pp. 1133-1137. doi: 10.35335/mantik.Vol4.2020.915.pp1133-1137.

Syahputra, Z. 2022. Implementasi Deteksi Wajah pada Sistem Absensi Dengan Menerapkan

Teknik Face Recognition. SNASTIKOM Ke 9 Oktober Tahun 2022

Rahman, Fina Afifana (2020) Klasifikasi Invasive Ductal Carcinoma Menggunakan Convolutional Neural Network. Skripsi, Universitas Muhammadiyah Malang.

Wijaya, N., & Ridwan, A. (2019). Klasifikasi Jenis Buah Apel Dengan Metode KNearest Neighbors Dengan Ekstraksi Fitur HSV dan LBP. Jurnal Sisfokom (Sistem Informasi dan Komputer), 8(1), 74-78.

Zeng, G. (2017, October). Fruit and vegetables classification system using image saliency and convolutional neural network. In 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC) (pp. 613-617). IEEE.