Maize Kernel Quality Detection Based on Improved Lightweight YOLOv7

As an important cereal crop, maize is a versatile and multi-purpose crop, primarily used as a feed globally, but also is important as a food crop, and has other uses such as oil and industrial raw materials. Quality detection is an indispensable part of functional and usage classification, avoiding significant waste as well as increasing the added value of the product. The research on algorithms for real-time, accurate, and non-destructive identification and localization of corn kernels based on quality classification and equipped with non-destructive algorithms suitable for embedding in intelligent agricultural machinery systems is a key step in improving the effective utilization rate of maize kernels. The difference in maize kernel quality leads to significant differences in price and economic benefits. This algorithm reduced unnecessary waste caused by the low efficiency and accuracy of manual and mechanical detection. Image datasets of four kinds of maize kernel quality were established and each image contains a total of about 20 kernels of different quality randomly distributed. Based on the self-built dataset, the YOLOv7-tiny, as the backbone network, was used to design a maize kernel detection and recognition model named “YOLOv7-MEF”. Firstly, the backbone feature layer of the algorithm was replaced by MobileNetV3 as the feature extraction backbone network. Secondly, ESE-Net was used to enhance feature extraction and obtain better generalization performance. Finally, the loss function was optimized and replaced with the Focal-EOIU loss function. The experiment showed that the improved algorithm achieved an accuracy of 98.94%, a recall of 96.42%, and a Frame Per Second (FPS) of 76.92 with a model size of 9.1 M. This algorithm greatly reduced the size of the model while ensuring high detection accuracy and has good real-time performance. It was suitable for deploying embedded track detection systems in agricultural machinery equipment, providing a powerful theoretical research method for efficient detection of corn kernel quality.