Accurate detection of wood defects plays a crucial role in optimizing wood utilization, minimizing corporate expenses, and safeguarding precious forest resources. To achieve precise identification of surface defects in wood, we present a novel approach called the Omni-dynamic convolution coordinate attention-based YOLO (ODCA-YOLO) model. This model incorporates an Omni-dimensional dynamic convolution-based coordinate attention (ODCA) mechanism, which significantly enhances its ability to detect small target defects and boosts its expressiveness. Furthermore, to reinforce the feature extraction and fusion capabilities of the ODCA-YOLO network, we introduce a highly efficient features extraction network block known as S-HorBlock. By integrating HorBlock into the ShuffleNet network, this design optimizes the overall performance. Our proposed ODCA-YOLO model was rigorously evaluated using an optimized wood surface defect dataset through ablation and comparison experiments. The results demonstrate the effectiveness of our approach, achieving an impressive 78.5% in the mean average precision (mAP) metric and showing a remarkable 9% improvement in mAP compared to the original algorithm. Our proposed model can satisfy the need for accurate detection of wood surface defects.

The detection of wood defect is a crucial step in wood processing and manufacturing, determining the quality and reliability of wood products. To achieve accurate wood defect detection, a novel method named BPN-YOLO is proposed. The ordinary convolution in the ELAN module of the YOLOv7 backbone network is replaced with Pconv partial convolution, resulting in the P-ELAN module. Wood defect detection performance is improved by this modification while unnecessary redundant computations and memory accesses are reduced. Additionally, the Biformer attention mechanism is introduced to achieve more flexible computation allocation and content awareness. The IOU loss function is replaced with the NWD loss function, addressing the sensitivity of the IOU loss function to small defect location fluctuations. The BPN-YOLO model has been rigorously evaluated using an optimized wood defect dataset, and ablation and comparison experiments have been performed. The experimental results show that the mean average precision (mAP) of BPN-YOLO is improved by 7.4% relative to the original algorithm, which can better meet the need to accurately detecting surface defects on wood.

The detection of defects on the surface is of great importance for both the production and the application of strip steel. In order to detect the defects accurately, an improved YOLOv7-based model for detecting strip steel surface defects is developed. To enhances the ability of the model to extract features and identify small features, the ConvNeXt module is introduced to the backbone network structure, and the attention mechanism is embedded in the pooling module. To reduce the size and improves the inference speed of the model, an improved C3 module was used to replace the ELAN module in the head. The experimental results show that, compared with the original models, the mAP of the proposed model reached 82.9% and improved by 6.6%. The proposed model can satisfy the need for accurate detection and identification of strip steel surface defects.

Accurate detection of wood surface defects plays a pivotal role in enhancing wood grade sorting precision, maintaining high standards in wood processing quality, and safeguarding forest resources. This paper introduces an efficient and precise approach to detecting wood surface defects, building upon enhancements to the YOLOv8 model, which demonstrates significant performance enhancements in handling multi-scale and small-target defects commonly found in wood. The proposed method incorporates the dilation-wise residual (DWR) module in the trunk and the deformable large kernel attention (DLKA) module in the neck of the YOLOv8 architecture to enhance the network’s capability in extracting and fusing multi-scale defective features. To further improve the detection accuracy of small-target defects, the model replaces all the detector heads of YOLOv8 with dynamic heads and adds an additional small-target dynamic detector head in the shallower layers. Additionally, to facilitate faster and more-efficient regression, the original complete intersection over union (CIoU) loss function of YOLOv8 is replaced with the IoU with minimum points distance (MPDIoU) loss function. Experimental results indicate that compared with the YOLOv8n baseline model, the proposed method improves the mean average precision (mAP) by 5.5%, with enhanced detection accuracy across all seven defect types tested. These findings suggest that the proposed model exhibits a superior ability to detect wood surface defects accurately.

In the research of Facial Expression Recognition (FER), the inter-class of facial expression data is not evenly distributed, the features extracted by networks are insufficient, and the FER accuracy and speed are relatively low for practical applications. Therefore, a lightweight and efficient method based on class-rebalancing fusion cumulative learning for FER is proposed in our research. A dual-branch network (Regular feature learning and Rebalancing-Cumulative learning Network, RLR-CNet) is proposed, where the RLR-CNet uses the improvement in the lightweight ShuffleNet with two branches (feature learning and class-rebalancing) based on cumulative learning, which improves the efficiency of our model recognition. Then, to enhance the generalizability of our model and pursue better recognition efficiency in real scenes, a random masking method is improved to process datasets. Finally, in order to extract local detailed features and further improve FER efficiency, a shuffle attention module (SA) is embedded in the model. The results demonstrate that the recognition accuracy of our RLR-CNet is 71.14%, 98.04%, and 87.93% on FER2013, CK+, and RAF-DB, respectively. Compared with other FER methods, our method has great recognition accuracy, and the number of parameters is only 1.02 MB, which is 17.74% lower than that in the original ShuffleNet.