Accurate diagnosis of pear tree nutrient deficiency symptoms is vital for the timely adoption of fertilization and treatment. This study proposes a novel method on the fused feature multi-head attention recording network with image depth and shallow feature fusion for diagnosing nutrient deficiency symptoms in pear leaves. First, the shallow features of nutrient-deficient pear leaf images are extracted using manual feature extraction methods, and the depth features are extracted by the deep network model. Second, the shallow features are fused with the depth features using serial fusion. In addition, the fused features are trained using three classification algorithms, F-Net, FC-Net, and FA-Net, proposed in this paper. Finally, we compare the performance of single feature-based and fusion feature-based identification algorithms in the nutrient-deficient pear leaf diagnostic task. The best classification performance is achieved by fusing the depth features output from the ConvNeXt-Base deep network model with shallow features using the proposed FA-Net network, which improved the average accuracy by 15.34 and 10.19 percentage points, respectively, compared with the original ConvNeXt-Base model and the shallow feature-based recognition model. The result can accurately recognize pear leaf deficiency images by providing a theoretical foundation for identifying plant nutrient-deficient leaves.

Bamboo is an important economic crop with up to a large number of species. The distribution of bamboo species is wide; therefore, it is difficult to collect images and make the recognition model of a bamboo species with few amount of images. In this paper, nineteen species of bamboo with a total of 3220 images are collected and divided into a training dataset, a validation dataset and a test dataset. The main structure of a residual vision transformer algorithm named ReVI is improved by combining the convolution and residual mechanisms with a vision transformer network (ViT). This experiment explores the effect of reducing the amount of bamboo training data on the performance of ReVI and ViT on the bamboo dataset. The ReVI has a better generalization of a deep model with small-scale bamboo training data than ViT. The performances of each bamboo species under the ReVI, ViT, ResNet18, VGG16, Densenet121, Xception were then compared, which showed that ReVI performed the best, with an average accuracy of 90.21%, and the reasons for the poor performance of some species are discussed. It was found that ReVI offered the efficient identification of bamboo species with few images. Therefore, the ReVI algorithm proposed in this manuscript offers the possibility of accurate and intelligent classification and recognition of bamboo resource images.