BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation.

Abstract

The segmentation of pepper leaves from pepper images is of great significance for the accurate control of pepper leaf diseases. To address the issue, we propose a bidirectional attention fusion network combing the convolution neural network (CNN) and Swin Transformer, called BAF-Net, to segment the pepper leaf image. Specially, BAF-Net first uses a multi-scale fusion feature (MSFF) branch to extract the long-range dependencies by constructing the cascaded Swin Transformer-based and CNN-based block, which is based on the U-shape architecture. Then, it uses a full-scale feature fusion (FSFF) branch to enhance the boundary information and attain the detailed information. Finally, an adaptive bidirectional attention module is designed to bridge the relation of the MSFF and FSFF features. The results on four pepper leaf datasets demonstrated that our model obtains F1 scores of 96.75%, 91.10%, 97.34% and 94.42%, and IoU of 95.68%, 86.76%, 96.12% and 91.44%, respectively. Compared to the state-of-the-art models, the proposed model achieves better segmentation performance. The code will be available at the website: https://github.com/fangchj2002/BAF-Net.

Plant phenotyping relevance

ペッパー葉画像から葉領域を抽出する画像解析手法を開発・検証しており、植物器官の形態状態取得が研究の中心である。

Code and data availability

The paper's authors state that the BAF-Net segmentation code will be available at their GitHub URL (https://github.com/fangchj2002/BAF-Net), which is a paper-specific analysis code asset. The pepper leaf image dataset itself has no public deposit statement, and LabelMe is a generic third-party annotation tool, not a论文-