CLASSIFICATION OF THE RITH TEXTURE OF TANDUK BANANAS BASED ON THE LEVEL OF COLOR BRIGHTNESS USING THE CONVOLUTIONAL NEURAL NETWORK METHOD

WIJAYA, PURWANDIAS HENDY (2026) CLASSIFICATION OF THE RITH TEXTURE OF TANDUK BANANAS BASED ON THE LEVEL OF COLOR BRIGHTNESS USING THE CONVOLUTIONAL NEURAL NETWORK METHOD. Tugas Akhir thesis, University of Technology Yogyakarta.

Text 5190411571_Purwandias Hendy Wijaya_Abstrak.pdf Download (131kB)

Abstract

ABSTRACT The Horn Banana variety (Musa paradisiaca fa. corniculata) is commonly found and cultivated in Indonesia due to its adaptability to tropical climates. This variety is popular for its large size and distinctive cylindrical shape, which is slightly curved, with well-defined angular edges that taper to a pointed tip. Its skin is smooth, thick, and firm. Indonesia ranks among the top countries worldwide in horn banana cultivation. After harvesting, bananas are sorted by ripeness based on changes in skin color. While the human eye can visually assess ripeness, the large volume of harvests poses challenges for quick, consistent, and reliable decision-making about whether bananas are unripe, ripe, overripe, or rotten. Therefore, an automated method is needed to classify banana ripeness using image processing, specifically employing Convolutional Neural Networks (CNNs). This study focuses on developing a classification system to categorize horn bananas into five ripeness levels: unripe, half-ripe, ripe, overripe, and rotten. Keywords: Horn Banana, Classification, Image Processing, Convolutional Neural Network, Identification

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General) > T201 Patents. Trademarks
Divisions:	Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User:	Kaprodi S1 Informatika UTY
Date Deposited:	05 May 2026 02:10
Last Modified:	05 May 2026 02:10
URI:	http://eprints.uty.ac.id/id/eprint/19762

Actions (login required)

View Item