Back

The Alexnet-ResNet-Inception Network for Classifying Fruit Images

wenzhong, l.

2020-02-10 bioinformatics
10.1101/2020.02.09.941039 bioRxiv
Show abstract

Fruit classification is conductive to improving the self-checkout and packaging systems. The convolutional neural networks automatically extract features through the direct processing of original images, which has attracted extensive attention from researchers in fruit classification. However, due to the similarity of fruit color, it is difficult to recognize at a higher accuracy. In the present study, a deep learning network, Interfruit, was built to classify various types of fruit images. A fruit dataset involving 40 categories was also constructed to train the network model and to assess its performance. According to the evaluation results, the overall accuracy of Interfruit reached 93.17% in the test set, which was superior to that of several advanced methods. According to the findings, the classification system, Interfruit, recognizes fruits with high accuracy, which has a broad application prospect.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.