A Recognition Model Based on Multiscale Feature Fusion for Needle-Shaped <i>Bidens</i> L. Seeds
Zizhao Zhang,
Yiqi Huang,
Ying Chen,
Ze Liu,
Bo Liu,
Conghui Liu,
Cong Huang,
Wanqiang Qian,
Shuo Zhang,
Xi Qiao
Affiliations
Zizhao Zhang
College of Mechanical Engineering, Guangxi University, Nanning 530004, China
Yiqi Huang
College of Mechanical Engineering, Guangxi University, Nanning 530004, China
Ying Chen
College of Mechanical Engineering, Guangxi University, Nanning 530004, China
Ze Liu
College of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, China
Bo Liu
Shenzhen Branch, Guangdong Laboratory of Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen 518120, China
Conghui Liu
Shenzhen Branch, Guangdong Laboratory of Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen 518120, China
Cong Huang
Shenzhen Branch, Guangdong Laboratory of Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen 518120, China
Wanqiang Qian
Shenzhen Branch, Guangdong Laboratory of Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen 518120, China
Shuo Zhang
College of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, China
Xi Qiao
College of Mechanical Engineering, Guangxi University, Nanning 530004, China
To solve the problem that traditional seed recognition methods are not completely suitable for needle-shaped seeds, such as Bidens L., in agricultural production, this paper proposes a model construction idea that combines the advantages of deep residual models in extracting high-level abstract features with multiscale feature extraction fusion, taking into account the depth and width of the network. Based on this, a multiscale feature fusion deep residual network (MSFF-ResNet) is proposed, and image segmentation is performed before classification. The image segmentation is performed by a popular semantic segmentation method, U2Net, which accurately separates seeds from the background. The multiscale feature fusion network is a deep residual model based on a residual network of 34 layers (ResNet34), and it contains a multiscale feature fusion module and an attention mechanism. The multiscale feature fusion module is designed to extract features of different scales of needle-shaped seeds, while the attention mechanism is used to improve the ability to select features of our model so that the model can pay more attention to the key features. The results show that the average accuracy and average F1-score of the multiscale feature fusion deep residual network on the test set are 93.81% and 94.44%, respectively, and the numbers of floating-point operations per second (FLOPs) and parameters are 5.95 G and 6.15 M, respectively. Compared to other deep residual networks, the multiscale feature fusion deep residual network achieves the highest classification accuracy. Therefore, the network proposed in this paper can classify needle-shaped seeds efficiently and provide a reference for seed recognition in agriculture.
