Application of Improved Lightweight Network and Choquet Fuzzy Ensemble Technology for Soybean Disease Identification

Abstract

The identification of soybean disease images in natural scenes has been a challenging task due to their complex backgrounds and diverse spot patterns. Traditional single convolutional neural network (CNN) for soybean disease image recognition often cannot have both high identification accuracy and strong generalization ability. Therefore, this paper focuses on the classification of soybean leaf diseases using improved lightweight networks for transfer learning, and improves the identification accuracy and precision by introducing Choquet fuzzy ensemble strategy. First, the convolutional long short-term memory (ConvLSTM) layer and the squeeze and excitation (SE) block are introduced into the four original lightweight models (Xception, MobileNetV2, NASNetMobile, MobileNet) to improve the network's ability to grasp image features, and then the classification confidence scores obtained from the improved lightweight networks are fed into the fuzzy iensemble network to complete the aggregation of the final results. In order to improve the performance of the model and enrich the distribution of samples in the highdimensional feature space, this paper converts soybean healthy leaf images to diseased leaf images using an unsupervised image translation method based on Cycle-Consistent Adversarial Networks (CycleGAN). The results show that the improved lightweight model has higher recognition accuracy than the original network. The proposed fuzzy ensemble model obtains 94.27% recognition accuracy and an average F1-score of 94% in the soybean leaf disease classification task, which is better than a single model and other ensemble methods. It has a good application prospect and initially meets the production requirements of soybean disease identification.INDEX TERMS Choquet integral; CycleGAN; Fuzzy ensemble; Soybean leaf diseases.

Leaf Segmentation Using Modified YOLOv8-Seg Models

“…For example, Bin Wang used a parallel two-way convolutional neural network to classify the leaf category in Flavia [ 4 ], Swedish [ 5 ], and Leafsnap [ 6 ] datasets and achieved above 91% performance in all three datasets [ 7 ]. Various types of deep convolution networks were employed in leaf classification tasks such as lightweight CNN [ 8 ], Siamese network [ 9 ], and ResNet [ 10 , 11 ]. These works show that for isolated leaf segmentation and identification, if the images are taken carefully with only one leaf in the center and a clear background, researchers can achieve very good performance in their tasks even if they omit the segmentation or detection stage.…”