In view of the time-consuming and laborious manual picking and sorting of strawberries, the direct impact of image recognition accuracy on automatic picking and the rapid development of deep learning(DL), a Faster Regions with Convolutional Neural Network features (R-CNN) strawberry recognition method that combines Mixup data augmentation, a ResNet(Residual Network)50 backbone feature extraction network and a Soft-NMS (Non-Maximum Suppression) algorithm, named the MRS Faster R-CNN, is proposed. In this paper, the transfer learning backbone feature extraction network VGG (Visual Geometry Group) 16 and ResNet50 are compared, and the superior ResNet50 is selected as the backbone network of MRS Faster R-CNN. The data augmentation method of Mixup image fusion is used to improve the learning and generalization ability of the model. The redundant bboxes (bounding boxes) are removed through Soft-NMS to obtain the best region proposal. The freezing phase is added to the training process, effectively reducing the occupation of video memory and shortening the training time. After experimental verification, the optimized model improved the AP (Average Precision) values of mature and immature strawberries by 0.26% and 5.34%, respectively, and the P(Precision) values by 0.81% and 6.34%, respectively, compared to the original model (R Faster R-CNN). Therefore, the MRS Faster R-CNN model proposed in this paper has great potential in the field of strawberry recognition and maturity classification and improves the recognition rate of small fruit and overlapping occluded fruit, thus providing an excellent solution for mechanized picking and sorting.

Due to the difficulty in distinguishing transparent and white foreign fibers from seed cotton in RGB images and in order to improve the recognition ability of deep learning (DL) algorithms for white, transparent, and multi-class mixed foreign fibers with different sizes in seed cotton, this paper proposes a method of combining hyperspectral imaging technology with a multi-module joint hierarchical residue network (MJHResNet). Firstly, a series of preprocessing methods are performed on the hyperspectral image (HSI) to reduce the interference of noise. Secondly, a double-hierarchical residual (DHR) structure is designed, which can not only obtain multi-scale information, but also avoid gradient vanishing to some extent. After that, a squeeze-and-excitation network (SENet) is integrated to reduce redundant information, improve the expression of model features, and improve the accuracy of foreign fiber identification in seed cotton. Finally, by analyzing the experimental results with advanced classifiers, this method has significant advantages. The average accuracy is 98.71% and the overall accuracy is 99.28%. This method has great potential for application in the field of foreign fiber identification in seed cotton.