Evaluation of beef crispiness by models based on deep learning

Red meat, having all kinds of essential amino acids needed by humans and as one of the main sources of protein for human societies, has long been of great importance in the human diet, this special place has made the need to provide healthy and high-quality materials more urgent than ever. One of the most important and practical techniques for evaluating meat quality is studying its appearance and physical characteristics. This research designed and implemented a model based on convolutional neural networks based on three structures: Mobile Net, InceptionV3, and VGG16. In this research, the shear resistance value of each meat sample was measured by the Warner-Bratzler method, and input data for training and evaluation of the convolutional neural networks were digital images taken by the LG model smartphone (LG G4 H815) in uncontrolled conditions and independent of the environment and light. In the end, the designed models were able to classify the prototypes based on the extracted features with acceptable accuracy. The performance of the designed models was evaluated with statistical indicators of accuracy, precision, sensitivity, and specificity, and the best classification model was the model designed based on the structure of the Mobile Net, which was able to classify image data with an accuracy of 92.61%.