Research on Quality Classification of Fruits and Vegetables Based on Transfer Learning

• 1、School of Computer Science Technology,Shandong University of Technology,Zibo 255049

Abstract：Aiming at the difficulties in feature extraction of traditional fruit and vegetable quality classifi-cation models, long training time and low classification accuracy, a migration learning image classification method based on support vector machine and pre-trained VGG16 deep learning network hybrid model is proposed. On the basis of migration learning, SVM is used to replace the fully connected layer and Softmax classification layer of the VGG16 network for classification, forming a new feature extraction-feature classification (VGG16-SVM) model structure. Using this method, the classification accuracy rate on the test set is 99.1%, and the AUC (the area under ROC curve) value reaches 0.9996. Compared with ordinary convolutional neural networks and various machine learning models, it is verified that this method can effectively improve the training speed and classification accuracy of fruit and vegetable quality classification models.

Keywords： Computer Application Technology VGG16 deep learning network transfer learning support vector machine image classification