Image Classification Modelling of Beef and Pork Using Convolutional Neural Network

Abstract

The high price of beef makes some people manipulate sales in markets or other shopping venues, such as mixing beef and pork. The difference between pork and beef is actually from the color and texture of the meat. However, many people do not understand these differences yet. One of the solutions is to create a technology that can recognize and differentiate pork and beef. That is what underlies this research to build a system that can classify the two types of meat. Since traditional machine learning such as Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) uses manual feature extraction in pattern recognition, we use Convolutional Neural Network (CNN) that can extract the feature automatically through the convolution layer. CNN is one of the deep learning methods and the development of artificial intelligence science that can be applied to classify images. There is no research on using CNN for pork and beef classification. Several regularization techniques, including dropout, L2, and max-norm with several values in them are applied to the model and compared to get the best classification results and can predict new data accurately. The best accuracy of 97.56% and the lowest loss of 0.111 were obtained from the CNN model by applying the dropout technique using p=0.7 supported by hyperparameters such as two convolution layers, 128 neurons in the fully connected layer, ReLU activation function, and two fully connected layers. The results of this study are expected to be the basis for making beef and pork recognition applications.