Fruit Recognition Based on Convolution Neural Network

Abstract

Traditional fruit recognition is mainly manual, which is not conducive to automation. Deep convolution neural network (DCNN) has a strong ability of feature learning and expression. It is helpful to realize intelligence in fruit sales market if it is applied to the identification of fruits. Due to the lack of standard image databases and various types of fruits, image data sets used in this paper are obtained through taking pictures of fruits and network download. Considering the small number of samples, in addition to using common image processing technology for data expansion, transfer learning technology based on vgg16 model is also adopted for fine tuning, which can reduce the training time and alleviate over fitting. Finally, six kinds of common fruits are chosen for experiments, and the test results show that the average recognition accuracy reaches 94.16%.