Fruit category classification by fractional Fourier entropy with rotation angle vector grid and stacked sparse autoencoder

Aim Fruit category classification is important in factory packing and transportation, price prediction, dietary intake, so forth. Methods This study proposed a novel artificial intelligence system to classify fruit categories. First, 2D fractional Fourier entropy with rotation angle vector grid was used extract features from images. Afterwards, five-layer stacked sparse autoencoder as the classifier. Results Ten runs on test set showed our method achieved micro-averaged F1 score of 95.08% for an 18-category dataset. Conclusion Our gives better than 10 state-of-the-art approaches.