Classification of seed corn ears based on custom lightweight convolutional neural network and improved training strategies

Abnormal ears (containing phenotypic differences in seeds, particularly in color) are manually removed to improve seed purity during seed production in the field or factory. Traditional convolutional neural networks (CNN) have significant parameters and greater network depth, making them unsuitable for deployment in resource-constrained embedded devices. This paper proposes a deep learning model (CornNet) based on custom lightweight CNN and improved training strategies for corn ears classification to address this issue. We improved the structure of VGG16 by reducing the number of convolution layers (Conv) and its channels to change network depth and used the global average pooling layer (GAP) instead of the fully connected layer (FC) to achieve a lightweight model. The Squeeze-and-Excitation network (SE) and Batch Normalization (BN) were used to improve the feature extraction ability and prevent gradient disappearance. The image acquisition environment, similar to the production line, was constructed to obtain images with consistent features to reduce the data required for training. Two training strategies (i.e., data augmentation and dynamic learning rate) were optimized to improve performance. The results showed that CornNet performed well compared to MobileNet, ShuffleNet, VGG16, ResNet50 and AlexNet in terms of accuracy, F1-score, model size, and FLOPs of 98.56 %, 98.93 %, 0.42MB and 0.07G, respectively. The improved training strategies improved accuracy by 3.07% to 16.08% and 0.26% to 30.91%. The CornNet proposed in this paper achieved a good balance between performance and computational cost, and it can obtain better generalization ability on small datasets than the traditional deeper networks model.