Rice is one of the most important crops for food supply, and there are multiple differences in the quality of rice in different geographic regions, which have a significant impact on subsequent yields and economic benefits. The traditional rice identification methods are time-consuming, inefficient, and delicate. This study proposes a deep learning-based method for fast and non-destructive classification of rice grown in different geographic environments. The experiment collected rice with the name of Ji-Japonica 830 from 10 different regions, and a total of 10,600 rice grains were obtained, and the fronts and backsides of the seeds were photographed with a camera in batches, and a total of 30,000 images were obtained by preprocessing the data. The proposed improved residual network architecture, High-precision Residual Network (HResNet), was used to compare the performance of the models. The results showed that HResNet obtained the highest classification accuracy result of 95.13%, which is an improvement of 7.56% accuracy with respect to the original model, and validation showed that HResNet achieves a 98.7% accuracy in the identification of rice grown in different soil classes. The experimental results show that the proposed network model can effectively recognize and classify rice grown in different soil categories. It can provide a reference for the identification of other crops and can be applied for consumer and food industry use.

Strawberry (Fragaria × ananassa), a nutrient-dense fruit with significant economic value in commercial cultivation, faces critical detection challenges in automated harvesting due to complex growth conditions such as foliage occlusion and variable illumination. To address these limitations, this study proposes Ripe-Detection, a novel lightweight object detection framework integrating three key innovations: a PEDblock detection head architecture with depth-adaptive feature learning capability, an ADown downsampling method for enhanced detail perception with reduced computational overhead, and BiFPN-based hierarchical feature fusion with learnable weighting mechanisms. Developed using a purpose-built dataset of 1021 annotated strawberry images (Fragaria × ananassa ‘Red Face’ and ‘Sachinoka’ varieties) from Changchun Xiaohongmao Plantation and augmented through targeted strategies to enhance model robustness, the framework demonstrates superior performance over existing lightweight detectors, achieving mAP50 improvements of 13.0%, 9.2%, and 3.9% against YOLOv7-tiny, YOLOv10n, and YOLOv11n, respectively. Remarkably, the architecture attains 96.4% mAP50 with only 1.3M parameters (57% reduction from baseline) and 4.4 GFLOPs (46% lower computation), simultaneously enhancing accuracy while significantly reducing resource requirements, thereby providing a robust technical foundation for automated ripeness assessment and precision harvesting in agricultural robotics.

Crop yields are influenced by various factors, including seed quality and environmental conditions. Detecting seed vigor is a critical task for seed researchers, as it plays a vital role in seed quality assessment. Traditionally, this evaluation was performed manually, which is time-consuming and labor-intensive. To address this limitation, this study integrates the ConvUpDownModule (a customized convolutional module), C2f-DSConv(C2f module with Integrated Dynamic Snake Convolution), and T-SPPF (the SPPF module integrated with the transformer multi-head attention mechanism) into the VT-YOLOv8-Seg network (the improved YOLOv8-Seg Network), an enhancement of the YOLOv8-Seg architecture. The ConvUpDownModule reduces the computational complexity and model parameters. The C2f-DSConv leverages flexible convolutional kernels to enhance the accuracy of maize germ edge segmentation. The T-SPPF integrates global information to improve multi-scale segmentation performance. The proposed model is designed for detecting and segmenting maize seeds and germs, facilitating seed germination detection and germination speed computation. In detection tasks, the VT-YOLOv8-Seg model achieved 97.3% accuracy, 97.9% recall, and 98.5% mAP50, while in segmentation tasks, it demonstrated 97.2% accuracy, 97.7% recall, and 98.2% mAP50. Comparative experiments with Mask R-CNN, YOLOv5-Seg, and YOLOv7-Seg further validated the superior performance of our model in both detection and segmentation. Additionally, the impact of seed aging on maize seed growth and development was investigated through artificial aging studies. Key metrics such as germination rate and germ growth speed, both closely associated with germination vigor, were analyzed, demonstrating the effectiveness of the proposed approach for seed vigor assessment.