基于Siamese-YOLOv4的印刷品缺陷目标检测

在印刷工业生产中，针对直接使用YOLOv4网络进行印刷缺陷目标检测精度低、所需训练样本数量大的问题，提出了一种基于Siamese-YOLOv4的印刷品缺陷目标检测方法。首先，使用了一种图像分割和随机参数变化的策略对数据集进行增强；然后，在主干网络中增加了孪生相似性检测网络，并在相似性检测网络中引入Mish激活函数来计算出图像块的相似度，在此之后将相似度低于阈值的区域作为缺陷候选区域；最后，训练候选区域图像，从而实现缺陷目标的精确定位与分类。实验结果表明：Siamese-YOLOv4模型的检测精度优于主流的目标检测模型，在印刷缺陷数据集上，Siamese-YOLOv4网络对卫星墨滴缺陷的检测准确率为98.6%，对脏点缺陷的检测准确率为97.8%，对漏印缺陷的检测准确率为93.9%；检测的平均精度均值（mAP）达到了96.8%，相较于YOLOv4算法、Faster R-CNN算法、SSD算法、EfficientDet算法分别提高了6.5个百分点、6.4个百分点、14.9个百分点、10.6个百分点。所提Siamese-YOLOv4模型一方面在印刷品缺陷检测中有较低的误检率和漏检率，另一方面通过相似性检测网络计算图像块的相似度从而提高了检测的精度，表明所提缺陷检测方法可应用于印刷质检以提高印刷企业的缺陷检测水平。

Defect target detection for printed matter based on Siamese-YOLOv4

In the production of printing industry， using You Only Look Once version 4 （YOLOv4） directly to detect printing defect targets has low accuracy and requires a large number of training samples. In order to solve the problems， a defect target detection method for printed matter based on Siamese-YOLOv4 was proposed. Firstly， a strategy of image segmentation and random parameter change was used to enhance the dataset. Then， the Siamese similarity detection network was added to the backbone network， and the Mish activation function was introduced into the similarity detection network to calculate the similarity of image blocks. After that， the regions with similarity below the threshold were regarded as the defect candidate regions. Finally， the candidate region images were trained to achieve the precise positioning and classification of defect targets. Experimental results show that， the detection precision of the proposed Siamese-YOLOv4 model is better than those of the mainstream target detection models. On the printing defect dataset， the Siamese-YOLOv4 network has the detection precision for satellite ink droplet defect of 98.6%， the detection precision for dirty spot of 97.8%， the detection precision for print lack of 93.9%； and the mean Average Precision （mAP） reaches 96.8%， which is 6.5 percentage points，6.4 percentage points， 14.9 percentage points and 10.6 percentage points higher respectively than the YOLOv4 algorithm， the Faster Regional Convolutional Neural Network （Faster R-CNN） algorithm， the Single Shot multibox Detector （SSD） algorithm and the EfficientDet algorithm. The proposed Siamese-YOLOv4 model has low false positive rate and miss rate in the defect detection of printed matter， and improves the detection precision by calculating similarity of the image blocks through the similarity detection network， proving that the proposed defect detection method can be applied to the printing quality inspection and therefore improve the defect detection level of printing enterprises.