LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment

Robust watermarking requires finding invariant features under multiple attacks to ensure correct extraction.Deep learning has extremely powerful in extracting features,and watermarking algorithms based on deep learning have attracted widespread attention.Most existing methods use 3×3 small kernel convolution to extract image features and embed the watermarking.However,the effective perception fields for small kernel convolution are extremely confined,so the pixels that each watermarking can affect are restricted,thus limiting the performance of the watermarking.To address these problems,we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss functions.It uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a highdimensional space by 1×1 convolution to achieve adaptability in the channel dimension.Subsequently,the modification of the embedded watermarking on the cover image is extended to more pixels.Because the magnitude and convergence rates of each loss function are different,an adaptive loss weight assignment strategy is proposed to make theweights participate in the network training together and adjust theweight dynamically.Further,a high-frequency wavelet loss is proposed,by which the watermarking is restricted to only the low-frequency wavelet sub-bands,thereby enhancing the robustness of watermarking against image compression.The experimental results show that the peak signal-to-noise ratio(PSNR)of the encoded image reaches 40.12,the structural similarity(SSIM)reaches 0.9721,and the watermarking has good robustness against various types of noise.

基于改进YOLOv5的柑橘病虫害检测

[目的]柑橘叶片受到病菌感染或虫害侵袭后,导致柑橘树生长发育异常、产量减少甚至死亡。早期柑橘叶片病虫害检测有助于做好预防措施减少损失。[方法]实际检测过程中YOLOv5s模型存在定位不精确、背景复杂等问题,受VAN(visual attention network)模型的启发,引入LKA(large kernel attention)模块,对YOLOv5s模型进行改进。改进的YOLOv5s模型可实现对图像信息的集中关注和精细抽取;使用CARAFE轻量级算子替换常规的上采样方法,能够提高特征重建质量,解决尺度不匹配问题并提高检测性能;使用FReLU激活函数,能够捕捉更多的柑橘病虫害的关键特征,提高检测准确度。此外,还构建了一个包含炭疽病、溃疡病和受潜叶蝇病虫侵害的柑橘叶片数据集,采用该数据集进行试验。[结果]改进后的模型YOLOv5-LC对于柑橘病虫害的检测结果显示:平均检测精度mAP50达到94.5%,mAP50:95为84.3%,较原模型分别提高了2.0%和4.4%,模型大小仅为7.3 MB。准确率为93.8%,召回率84.5%,浮点运算次数仅为18.5 G。[结论]改进后的YOLOv5-LC模型可以更加准确检测出柑橘病虫害。

YOLO-RLC:An Advanced Target-Detection Algorithm for Surface Defects of Printed Circuit Boards Based on YOLOv5

Printed circuit boards(PCBs)provide stable connections between electronic components.However,defective printed circuit boards may cause the entire equipment system to malfunction,resulting in incalculable losses.Therefore,it is crucial to detect defective printed circuit boards during the generation process.Traditional detection methods have low accuracy in detecting subtle defects in complex background environments.In order to improve the detection accuracy of surface defects on industrial printed circuit boards,this paper proposes a residual large kernel network based on YOLOv5(You Only Look Once version 5)for PCBs surface defect detection,called YOLO-RLC(You Only Look Once-Residual Large Kernel).Build a deep large kernel backbone to expand the effective field of view,capture global informationmore efficiently,and use 1×1 convolutions to balance the depth of the model,improving feature extraction efficiency through reparameterization methods.The neck network introduces a bidirectional weighted feature fusion network,combined with a brand-new noise filter and feature enhancement extractor,to eliminate noise information generated by information fusion and recalibrate information from different channels to improve the quality of deep features.Simplify the aspect ratio of the bounding box to alleviate the issue of specificity values.After training and testing on the PCB defect dataset,our method achieved an average accuracy of 97.3%(mAP50)after multiple experiments,which is 4.1%higher than YOLOv5-S,with an average accuracy of 97.6%and an Frames Per Second of 76.7.The comparative analysis also proves the superior performance and feasibility of YOLO-RLC in PCB defect detection.

A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection

Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.