CD Skripsi
Implementasi Model Transfer Learning Mobilenet Untuk Klasifikasi Jenis Daging Sapi Dan Daging Babi
ABSTRACT
Indonesia is one of the countries with a relatively high level of meat consumption, as protein and nutrients are essential for society. However, problems such as the insufficient supply of beef compared to market demand and the increasing number of cases involving the adulteration of beef with pork have become major concerns. This issue not only causes economic losses for consumers but also raises serious concerns for communities with religious or cultural restrictions, such as Muslims, who are prohibited from consuming pork. One effort that can assist visually impaired individuals is the development of a machine learning model capable of classifying beef and pork. In this study, a pre-trained MobileNetV2 model was used as the basis for developing a classification model to distinguish between beef and pork images. The dataset used consisted of 6.168 images of beef and pork, which were divided into 70% for training data, 15% for validation data, and 15% for testing data. Model evaluation was conducted using a confusion matrix, resulting in an accuracy of 95.19%.
Keywords: Beef ,Pork, Pre-trained Model, MobileNetV2
Tidak tersedia versi lain