Identifikasi Kesegaran Ikan Nila menggunakan Metode Convolutional Neural Network (Cnn) Berdasarkan Warna Insang

IDOR, Simforianus (2026) Identifikasi Kesegaran Ikan Nila menggunakan Metode Convolutional Neural Network (Cnn) Berdasarkan Warna Insang. Undergraduate thesis, Universitas Katolik Widya Mandira.

	Text ABSTRAK.pdf Download (336kB)
	Text BAB I (1).pdf Download (486kB)
	Text BAB II.pdf Restricted to Repository staff only Download (619kB)
	Text BAB III.pdf Restricted to Repository staff only Download (851kB)
	Text BAB IV.pdf Restricted to Repository staff only Download (492kB)
	Text BAB V.pdf Restricted to Repository staff only Download (476kB)
	Text BAB VI.pdf Download (412kB)
	Text SURAT KETERANGAN HASIL CEK PLAGIASI dan DAFTAR PUSTAKA.pdf Download (593kB)
	Text ABSTRAK.pdf Download (819kB)

Abstract

Fish freshness is an important factor that determines the quality and safety of tilapia consumption. Manual fish freshness assessment still relies on human experience, so an automated system that can provide better results is needed. This study aims to identify the freshness level of tilapia using the Convolutional Neural Network (CNN) method based on gill color images. To facilitate use, this system is equipped with a userfriendly Graphical User Interface (GUI), allowing users to upload gill images and receive identification results directly. The dataset used in this study consists of 120 tilapia gill images divided into three classification classes: fresh fish, stale fish, and rotten fish. The data is divided into 90 images as training data and 30 images as test data. All images were taken at a distance of 10 cm from the left and right sides of the gills with uniform lighting, then preprocessed and standardized to a size of 224 × 224 pixels before being used in the training and testing process of the CNN model. The training results showed that the CNN model achieved 100% validation accuracy with a loss value close to zero, indicating optimal learning. Based on the test results on the three classification classes, the CNN model performed very well in classifying tilapia freshness levels. Therefore, it can be concluded that the CNN method is effective in classifying tilapia freshness levels based on gill color images.

Actions (login required)

View Item