KLASIFIKASI JENIS BUAH-BUAHAN MENGGUNAKAN CITRA DIGITAL DENGAN METODE CONVOLUTIONAL NEURAL NETWORKS (CNN)

IHSAN, ALIF MUHAMMAD (2023) KLASIFIKASI JENIS BUAH-BUAHAN MENGGUNAKAN CITRA DIGITAL DENGAN METODE CONVOLUTIONAL NEURAL NETWORKS (CNN). S1 thesis, Universitas Mercu Buana Bekasi.

[img]
Preview
Text
41519210017 - ALIF MUHAMMAD IHSAN - 01 Cover.pdf

Download (308kB) | Preview
[img]
Preview
Text
41519210017 - ALIF MUHAMMAD IHSAN - 02 Abstrak.pdf

Download (29kB) | Preview
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 03 BAB 1.pdf
Restricted to Registered users only

Download (85kB)
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 04 BAB 2.pdf
Restricted to Registered users only

Download (143kB)
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 05 BAB 3.pdf
Restricted to Registered users only

Download (129kB)
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 06 BAB 4.pdf
Restricted to Registered users only

Download (457kB)
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 07 BAB 5.pdf
Restricted to Registered users only

Download (26kB)
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 08 Daftar Pustaka.pdf
Restricted to Registered users only

Download (174kB)
[img] Text
41519210017 - ALIF MUHAMMAD IHSAN - 09 Lampiran.pdf
Restricted to Registered users only

Download (1MB)

Abstract

Hortikultura merupakan salah satu sub sektor pertanian yang dinilai sangat potensial untuk dikembangkan. Sejak merebaknya pandemi, permintaan komoditas hortikultura khususnya pada jenis Frutikultur (buah-buahan) cenderung meningkat karena perubahan pola konsumsi masyarakat. Masyarakat dan pola konsumsi tidak dapat dipisahkan karena apa yang dikonsumsi sehari-hari akan berpengaruh pada kualitas hidup masyarakat. Indonesia memiliki beragam jenis buah yang dikelompokkan menjadi 2, yakni jenis buah kering dan buah berdaging. Penelitian ini dibuat agar mempermudah konsumen untuk mengetahui citra data jenis buah kering dan buah berdaging yang tentunya berbeda. Convolutional Neural Network (CNN) adalah salah satu algoritma deep learning yang merupakan pengembangan dari Multilayer Perceptron (MPL) yang dirancang untuk mengolah data dalam bentuk dua dimensi, misalnya gambar atau suara. Metode CNN dapat diterapkan pada citra resolusi tinggi dengan model distribusi nonparametrik dan melakukan proses pembelajaran mandiri untuk pengenalan objek, ekstraksi objek, dan klasifikasi. Berdasarkan hasil penelitian dapat disimpulkan bahwa dataset buah kering dan berdaging telah dikumpulkan untuk melakukan prediksi. CNN dapat mengenali buah kering dan berdaging, untuk data testing 40% akurasi sebesar 91%, sedangkan untuk data testing 30% diperoleh akurasi 94%, dan untuk data testing 20% akurasi sebesar 86%. Kata Kunci: Convolutional Neural Network, Deep Learning, Pengolahan Citra, Klasifikasi Horticulture is one of the agricultural sub-sectors that is considered very potential to be developed. Since the outbreak of the pandemic, the demand for horticultural commodities, especially in the type of Fruticulture (fruits) tends to increase due to changes in people's consumption patterns. Society and consumption patterns cannot be separated because what is consumed daily will affect the quality of life of the community. Indonesia has various types of fruit which are categorized into 2 types, namely dried fruit and fleshy fruit. This research is made to make it easier for consumers to find out the image data of dried fruit and fleshy fruit types which are certainly different. Convolutional Neural Network (CNN) is one of the deep learning algorithms which is a development of Multilayer Perceptron (MPL) designed to process data in two-dimensional form, such as images or sounds. The CNN method can be applied to high-resolution images with nonparametric distribution models and performs a self-learning process for object recognition, object extraction, and classification. Based on the research results, it can be concluded that a dataset of dried and fleshy fruits has been collected to make predictions. CNN can recognize dried and fleshy fruits, for 40% testing data the accuracy is 91%, while for 30% testing data 94% accuracy is obtained, and for 20% testing data the accuracy is 86%. Keywords: Convolutional Neural Network, Deep Learning, Image Processing, Classification

Item Type: Thesis (S1)
Call Number CD: FIK/INFO 23 027
NIM/NIDN Creators: 41519210017
Uncontrolled Keywords: Convolutional Neural Network, Deep Learning, Pengolahan Citra, Klasifikasi
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: siti maisyaroh
Date Deposited: 27 Sep 2023 04:00
Last Modified: 27 Sep 2023 04:00
URI: http://repository.mercubuana.ac.id/id/eprint/81511

Actions (login required)

View Item View Item