AUTHOR=Yang Le , Xu Shuang , Yu XiaoYun , Long HuiBin , Zhang HuanHuan , Zhu YingWen TITLE=A new model based on improved VGG16 for corn weed identification JOURNAL=Frontiers in Plant Science VOLUME=Volume 14 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1205151 DOI=10.3389/fpls.2023.1205151 ISSN=1664-462X ABSTRACT=Weeds are still one of the most important factors affecting the yield and quality of corn in modern agricultural production. In order to use deep convolutional neural networks to accurately, efficiently and losslessly identify weeds in corn fields, a new corn weed identification model SE-VGG16 is proposed. The SE-VGG16 model takes VGG16 as the basis and adds the SE attention mechanism to realise that the network automatically focuses on the useful parts and allocates limited information processing resources to the important parts. Then the 3×3 convolutional kernels in the first block are reduced to 1×1 convolutional kernels, and the Relu activation function is replaced by Leaky Relu to perform feature extraction while dimensionality reduction. Finally, it is replaced by global average pooling layer for the fully connected layer of VGG16, and finally the output is performed by softmax. Experimental results verify that the SE-VGG16 model classifies corn weeds superiorly to other classical and advanced multiscale models with an average accuracy of 99.67%, more than the 97.75% of the original VGG16 model. Through the three evaluation indices of precision rate, recall rate and F1, it was concluded that SE-VGG16 has good robustness, high stability and high recognition rate, and the network model can be used to accurately identify weeds in corn fields, which can provide an effective solution for weed control in corn fields in practical applications.