Klasifikasi Ras Anjing Berdasarkan Citra Menggunakan Convolutional Neural Network

Abstract

Dogs are mammals that are much loved and kept. Dogs have 355 breeds worldwide. Each race has its own differences, but in certain races have little or almost similar differences. This study classifies 120 dog breeds using the Convolutional Neural Network (CNN) with the ResNet-50 architectural model and the Adam optimizer. The dataset used consists of 20580 images. The dataset is divided into training data, validation data, and test data with a ratio of 60:20:20. The resolution image is 224x224 pixels in size. In this study, it yielded an accuracy of 99,35%.