Klasifikasi Citra Daging Babi dan Daging Sapi Menggunakan Deep Learning Arsitektur ResNet-50 dengan Augmentasi Citra

Abstract

Beef is an example of an animal protein-rich food. The consumption of meat in Indonesia is increasing year after year, in tandem with the country's growing population. Many traders purposefully combine beef and pork in order to maximize profits. With the naked eye, it's difficult to tell the difference between pork and beef. In Muslim-majority countries, the assurance of halal meat is crucial. This study uses Deep Learning with the Convolutional Neural Network (CNN) method and ResNet-50 with data augmentation to classify images of beef and pork. The original meat picture databases contain 457 images, however following the data augmentation process, there are 2742 images in total, divided into three classes. The distribution of training and test data is 90 percent:10 percent in the comparison test scenario between the two original data schemes and supplemented data. With an average of 87.64 % accuracy, 87.59 % recall, and 90.90 % precision, the Confusion Matrix is the best classification performance model. There was no evidence of overfitting based on observations from the visualization of the training and testing process.

Penerapan Metode Convolutional Neural Network Untuk Klasifkasi Kualitas Daging Sapi Pada Aplikasi Berbasis Android

“…Setelah data terkumpul, citra-citra disesuaikan ukurannya dari yang sebelumnya berukuran 1280×720 menjadi 224×224 [17]. Setelah itu, dilakukan augmentasi data untuk memperbanyak citra yang digunakan dalam tahap pelatihan sehinggadapat mengoptimalkan kinerja metode CNN.…”

Classification of Beef and Pork with Deep Learning Approach

“…One other solution that can be used to distinguish beef and pork in addition to the above methods is to utilize deep learning methods. Some related research that has been done before is the identification of beef and pork with the Resnet-50 architecture which produces a model with an average accuracy of 87.64% [13]. Further research was conducted using EfficientNet-B0 and obtained an accuracy of 95.16% [14].…”