SCGNet: efficient sparsely connected group convolution network for wheat grains classification

Abstract

IntroductionEfficient and accurate varietal classification of wheat grains is crucial for maintaining varietal purity and reducing susceptibility to pests and diseases, thereby enhancing crop yield. Traditional manual and machine learning methods for wheat grain identification often suffer from inefficiencies and the use of large models. In this study, we propose a novel classification and recognition model called SCGNet, designed for rapid and efficient wheat grain classification.MethodsSpecifically, our proposed model incorporates several modules that enhance information exchange and feature multiplexing between group convolutions. This mechanism enables the network to gather feature information from each subgroup of the previous layer, facilitating effective utilization of upper-layer features. Additionally, we introduce sparsity in channel connections between groups to further reduce computational complexity without compromising accuracy. Furthermore, we design a novel classification output layer based on 3-D convolution, replacing the traditional maximum pooling layer and fully connected layer in conventional convolutional neural networks (CNNs). This modification results in more efficient classification output generation.ResultsWe conduct extensive experiments using a curated wheat grain dataset, demonstrating the superior performance of our proposed method. Our approach achieves an impressive accuracy of 99.56%, precision of 99.59%, recall of 99.55%, and an F1-score of 99.57%.DiscussionNotably, our method also exhibits the lowest number of Floating-Point Operations (FLOPs) and the number of parameters, making it a highly efficient solution for wheat grains classification.

Efficient residual network using hyperspectral images for corn variety identification

“…Researchers have utilized various methods to enhance the accuracy of image classification ( Ding et al., 2020 ; Ding et al., 2023 ). These methods include the use of hybrid convolutional networks ( Chen et al., 2020 ; Zhao et al., 2022a ; Zhao et al., 2022b ), innovative networks ( Sun et al., 2023 ; Zhang et al., 2023b ; Zhang et al., 2024b ), improving image resolution ( Paoletti et al., 2018 ; Liang et al., 2022 ), underwater image enhancement using different methods ( Li et al., 2019 ; Li et al., 2021 ), multimodal deep learning models ( Yao et al., 2023 ) and combining convolutional neural networks with hyperspectral images ( Cao et al., 2020 ; Zheng et al., 2020 ; Xi et al., 2022 ; Yao et al., 2022 ). Deep learning methods address the limitations of traditional approaches by automatically learning feature representations from raw data, eliminating the need for manual feature design.…”