Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM

Abstract

Identification technology of apple diseases is of great significance in improving production efficiency and quality. This paper has used apple Alternaria blotch and brown spot disease leaves as the research object and proposes a disease spot segmentation and disease identification method based on DFL-UNet+CBAM to address the problems of low recognition accuracy and poor performance of small spot segmentation in apple leaf disease recognition. The goal of this paper is to accurately prevent and control apple diseases, avoid fruit quality degradation and yield reduction, and reduce the resulting economic losses. DFL-UNet+CBAM model has employed a hybrid loss function of Dice Loss and Focal Loss as the loss function and added CBAM attention mechanism to both effective feature layers extracted by the backbone network and the results of the first upsampling, enhancing the model to rescale the inter-feature weighting relationships, enhance the channel features of leaf disease spots and suppressing the channel features of healthy parts of the leaf, and improving the network’s ability to extract disease features while also increasing model robustness. In general, after training, the average loss rate of the improved model decreases from 0.063 to 0.008 under the premise of ensuring the accuracy of image segmentation. The smaller the loss value is, the better the model is. In the lesion segmentation and disease identification test, MIoU was 91.07%, MPA was 95.58%, F1 Score was 95.16%, MIoU index increased by 1.96%, predicted disease area and actual disease area overlap increased, MPA increased by 1.06%, predicted category correctness increased, F1 Score increased by 1.14%, the number of correctly identified lesion pixels increased, and the segmentation result was more accurate. Specifically, compared to the original U-Net model, the segmentation of Alternaria blotch disease, the MIoU value increased by 4.41%, the MPA value increased by 4.13%, the Precision increased by 1.49%, the Recall increased by 4.13%, and the F1 Score increased by 2.81%; in the segmentation of brown spots, MIoU values increased by 1.18%, MPA values by 0.6%, Precision by 0.78%, Recall by 0.6%, and F1 Score by 0.69%. The spot diameter of the Alternaria blotch disease is 0.2-0.3cm in the early stage, 0.5-0.6cm in the middle and late stages, and the spot diameter of the brown spot disease is 0.3-3cm. Obviously, brown spot spots are larger than Alternaria blotch spots. The segmentation performance of smaller disease spots has increased more noticeably, according to the quantitative analysis results, proving that the model’s capacity to segment smaller disease spots has greatly improved. The findings demonstrate that for the detection of apple leaf diseases, the method suggested in this research has a greater recognition accuracy and better segmentation performance. The model in this paper can obtain more sophisticated semantic information in comparison to the traditional U-Net, further enhance the recognition accuracy and segmentation performance of apple leaf spots, and address the issues of low accuracy and low efficiency of conventional disease recognition methods as well as the challenging convergence of conventional deep convolutional networks.

RAAWC-UNet: an apple leaf and disease segmentation method based on residual attention and atrous spatial pyramid pooling improved UNet with weight compression loss

“…To validate the performance of the proposed network for apple leaf and disease segmentation in mixed environments, the results of the proposed network were compared with those of other different networks on the same datasets. FCN model ( Gao and Lin, 2019 ), SegNet mode ( Badrinarayanan et al., 2017 ), PSPNet model ( Zhu et al., 2021 ), DeepLabv3+ model ( Yuan et al., 2022 ), SwinUnet model ( Wang et al., 2022a ), UTNet model ( Gao et al., 2021 ), DFL-UNet +CBAM model ( Zhang et al., 2023 ), and TransUNet model ( Yan et al., 2023a ) are selected as the comparison methods. The above network architecture and proposed method are used to compare the effects of leaf and diseases segmentation on the same datasets.…”

“…A lightweight dense scale network (LDSNet) for corn leaf disease classification and recognition was proposed by Zeng Y et al ( Zeng et al., 2022 ), using different expansion rate convolutions and attention fusion methods to improve the recognition of leaves and diseases. The apple leaf and disease segmentation recognition model based on a hybrid loss function and the Convolutional Block Attention Module (CBAM) was proposed ( Zhang et al., 2023 ). The Swin Transformer is a network model for enhancing data and identifying cucumber leaf disease ( Wang et al., 2022a ).…”

Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation

“…To safeguard against the loss of the training model due to power outages or abnormal exits during long-term training, we propose a strategy to regularly save the model every 5 epochs. This approach ensures that even in such unfortunate events, the progress made during the training process is preserved (Zhang et al, 2023b).…”