Fitri Marisa, M. Ilham Setyo Wahyudi, Anastasia Lidya Maukar, Adriadi, Farida Yuliaty, Rina Novianty
(KNN) algorithm based on the extraction of visual characteristic features such as color, shape, texture, and spatial frequency. The dataset consists of 1,500 images categorized into three classes: Oranda, Ryukin, and Ranchu. Feature extraction includes HSV color histograms, Hu Moments for shape, GLCM for statistical texture, and Gabor filters for directional texture analysis. Classification was evaluated using several training and testing data ratios, and the results showed improved accuracy, especially with the inclusion of Gabor features. Experimental findings indicate that integrating these four features enhances the performance of the KNN algorithm in the goldfish image classification task, achieving a peak accuracy of 90% with an 80:20 train-test split ratio. © 2025 IEEE.
Widyagama University of Malang, Department of Informatics Engineering, Malang, Indonesia; President University, Industrial Engineering Study Program, Bekasi, Indonesia; Universitas Sangga Buana, Faculty of Engineering, Bandung, Indonesia; Universitas Sangga Buana, Bandung, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock