IDENTIFIKASI TINGKAT KEMATANGAN HASIL PANEN CABAI BERDASARKAN PENGOLAHAN CITRA DIGITAL MENGGUNAKAN JARINGAN SYARAF TIRUAN BACKPROPAGATION

Triwibowo, Rizki Yuli (2022) IDENTIFIKASI TINGKAT KEMATANGAN HASIL PANEN CABAI BERDASARKAN PENGOLAHAN CITRA DIGITAL MENGGUNAKAN JARINGAN SYARAF TIRUAN BACKPROPAGATION. Skripsi thesis, UNIVERSITAS BHAYANGKARA SURABAYA.

	Text 1714311055_cover_dalam.pdf Download (163kB)
	Text 1714311055_lembar_keaslian.pdf Download (94kB)
	Text 1714311055_lembar_pengesahan.pdf Download (96kB)
	Text 1714311055_lembar_persetujuan.pdf Download (66kB)
	Text 1714311055_bab1.pdf Download (284kB)

Abstract

Cayenne pepper it's one type of vegetable and has a high economic value. Seasonal changes greatly affect the price of cayenne pepper, in certain seasons the productivity of cayenne pepper decreases but the demand for market needs increases. This has resulted in several chili farmers competing to harvest cayenne pepper without paying attention to appropriate readiness for demand markets. This through preparation process is usually done manually by farmers so there are often differences in perceptions when sorting ripe. This causes errors, so to minimize these errors, a technology is needed by utilizing the use of digital images to determine the level of chili-based on color and texture using a backpropagation artificial network. An artificial neural network is a computational method that copies the workings of a human neural network that can learn. In this study, artificial neural networks will be combined with digital image processing technology. The image will be preprocessed then feature extraction is performed. The features used in this research are HSV color features and GLCM texture features. The results of feature extraction are used as input to the artificial neural network and testing is carried out by customizing the network parameters to get the maximum accuracy.This study used 3 types of models, color feature model with a learning rate customization of 0.5 gets an accuracy of 83.3%, texture feature model with a learning rate customization of 0.1 gets an accuracy of 60%, color and texture feature model with a learning rate customization 0.1 get an accuracy of 98.3%.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Cayenne pepper, Digital image processing, Artificial Neural Network, Backpropagation, GLCM
Subjects:	000 - COMPUTER SCIENCE, INFORMATIONS & GENERAL WORKS > 000 Computer science, information & general works > 003 Systems > 003.1 System Identification 000 - COMPUTER SCIENCE, INFORMATIONS & GENERAL WORKS > 000 Computer science, information & general works > 003 Systems > 003.1 System Identification
Divisions:	Faculty of Engineering > Bachelor of Informations Technology
Depositing User:	Perpus Ubhara Surabaya
Date Deposited:	14 Jan 2025 03:32
Last Modified:	14 Jan 2025 03:32
URI:	http://eprints.ubhara.ac.id/id/eprint/2853

Actions (login required)

View Item