Artificial recognition of tomato diseases is often time-consuming, laborious and subjective. For tomato disease images, it is difficult to find small discriminative features between different tomato diseases, which can bring challenges to fine-grained visual categorization of tomato leaf-based images. Therefore, we propose a novel model, which consists of 3 networks, including a Location network, a Feedback network, and a Classification network, named LFC-Net. At the same time, a self-supervision mechanism is proposed in the model, which can effectively detect informative regions of tomato image without the need for manual annotation such as bounding boxes/parts. Based on the consideration of the consistency between category of the image and informativeness of the image, we design a novel training paradigm. The Location network of the model first detects informative regions in the tomato image, and optimizes iterations under the guidance of the Feedback network. Then, the Classification network uses informative regions proposed by the Location network and the full image of the tomato for classification. Our model can be regarded as a multi-network collaboration, and networks can progress together. Compared with the pre-trained model on ImageNet, our model achieves the most advanced performance in the tomato dataset, with accuracy up to 99.7%. This work demonstrates that our model has a high accuracy and has the potential to be applied to other vegetable and fruit datasets, which can provide a reference for the prevention and control of tomato diseases.

The object detection method based on deep learning convolutional neural network (CNN) significantly improves the detection performance of wheat head on wheat images obtained from the near ground. Nevertheless, for wheat head images of different stages, high density, and overlaps captured by the aerial-scale unmanned aerial vehicle (UAV), the existing deep learning-based object detection methods often have poor detection effects. Since the receptive field of CNN is usually small, it is not conducive to capture global features. The visual Transformer can capture the global information of an image; hence we introduce Transformer to improve the detection effect and reduce the computation of the network. Three object detection networks based on Transformer are designed and developed, including the two-stage method FR-Transformer and the one-stage methods R-Transformer and Y-Transformer. Compared with various other prevalent object detection CNN methods, our FR-Transformer method outperforms them by 88.3% for AP₅₀ and 38.5% for AP₇₅. The experiments represent that the FR-Transformer method can gratify requirements of rapid and precise detection of wheat heads by the UAV in the field to a certain extent. These more relevant and direct information provide a reliable reference for further estimation of wheat yield.

Background: Pumpkin seeds are major oil crops with high nutritional value and high oil content. The collection and identification of different pumpkin germplasm resources play a significant role in the realization of precision breeding and variety improvement. In this research, we collected 75 species of pumpkin from the Zhejiang Province of China. 35,927 near-infrared hyperspectral images of 75 types of pumpkin seeds were used as the research object. Results: To realize the rapid classification of pumpkin seed varieties, position attention embedded three-dimensional convolutional neural network (PA-3DCNN) was designed based on hyperspectral image technology. The experimental results showed that PA-3DCNN had the best classification effect than other classical machine learning technology. The classification accuracy of 99.14% and 95.20% were severally reached on the training and test sets. We also demonstrated that the PA-3DCNN model performed well in next year’s classification with fine-tuning and met with 94.8% accuracy. Conclusions: The model performance improved by introducing double convolution and pooling structure and position attention module. Meanwhile, the generalization performance of the model was verified, which can be adopted for the classification of pumpkin seeds in multiple years. This study provided a new strategy and a feasible technical approach for identifying germplasm resources of pumpkin seeds.

The relevant comment texts of agricultural products sold on the e-commerce platform contain various and complex emotions of consumers, and reflect customers' consumer experience and views on those products. Compared with the features and advantages of English text segmentation structure, the analysis of Chinese sentiment polarity in a complex context has always been a problem in deep learning. This article explores the issue of sentiment polarity analysis of short texts of Chinese reviews of agricultural products by constructing Text-CNN, Bi-LSTM and BERT to fine-tune three deep learning models. The research object adopted is the review data of agricultural products on the e-commerce platform obtained based on crawler technology. The experimental results show that, compared with the Bi-LSTM and BERT fine-tuning models, the Text-CNN model's accuracy, precision, recall, and F1 value are all about 3 to 8 percentage points higher. The classification effect gradient gap between the three models is obvious. The accuracy of the Text-CNN convolutional neural network reached 99.92%. The results confirmed that Text-CNN has high sentiment analysis accuracy and good sentiment polarity classification effect in processing agricultural short text comment data, as an agricultural product e-commerce The emotional classification model of sales review data can provide an important reference for manufacturers to accurately distinguish user feedback and enhance market competitiveness.