Research Article
Apple Defect Detection Method Based on Convolutional Neural Network
5 downloads
@INPROCEEDINGS{10.1007/978-3-030-82562-1_37, author={Zheng Xu and Tao Shen and Shuhui Bi and Qinjun Zhao}, title={Apple Defect Detection Method Based on Convolutional Neural Network}, proceedings={Multimedia Technology and Enhanced Learning. Third EAI International Conference, ICMTEL 2021, Virtual Event, April 8--9, 2021, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2021}, month={7}, keywords={Deep learning Convolutional neural network Classification}, doi={10.1007/978-3-030-82562-1_37} }- Zheng Xu
Tao Shen
Shuhui Bi
Qinjun Zhao
Year: 2021
Apple Defect Detection Method Based on Convolutional Neural Network
ICMTEL
Springer
DOI: 10.1007/978-3-030-82562-1_37
Abstract
The appearance quality of apple is one of the important indicators for consumers to purchase. At present, the classification process of apple is still completed artificially, which not only wastes human resources, but also easily causes subjective misclassification. This paper proposes a convolutional neural network model to classify defective and defect-free apples. Apple images are collected by the smartphone camera, each type of apple has 312 images. The number of apple images is expanded through data enhancement technology, and randomly divided into training set, validation set, and test set according to the ratio of 6:2:2. The final classification accuracy is 99.2%.
Copyright © 2021–2025 ICST
