针对布匹瑕疵自动化检测,基于传统的机器视觉方法依赖于人工设计特征,对具有复杂背景图案的花色布瑕疵特征提取难度非常大,因此提出一种基于改进Faster R-CNN(faster region with convolutional neural network)的花色布瑕疵检测算法。...针对布匹瑕疵自动化检测,基于传统的机器视觉方法依赖于人工设计特征,对具有复杂背景图案的花色布瑕疵特征提取难度非常大,因此提出一种基于改进Faster R-CNN(faster region with convolutional neural network)的花色布瑕疵检测算法。在Faster R-CNN的基础上使用Resnet-50作为主干网络,嵌入可变形卷积来提高瑕疵特征的学习能力。通过设计多尺度模型来提高小瑕疵的检测,引入级联网络来提高瑕疵检测精度和定位准确度,构造优化的损失函数来降低样本不平衡影响。通过试验验证了该算法的有效性。结果表明,瑕疵检测效果准确率达94.97%,并能精准定位瑕疵位置,可满足工厂的实际需求。展开更多
为满足纺织业内机织印花布瑕疵检测的实时性需求,基于利用回归思想进行检测的单阶段算法模型YOLOv_(3)(you only look once version 3),提出一种改进的机织印花布疵点实时检测方法。通过优化骨干网络结构,引入可变形卷积,提高印花背景...为满足纺织业内机织印花布瑕疵检测的实时性需求,基于利用回归思想进行检测的单阶段算法模型YOLOv_(3)(you only look once version 3),提出一种改进的机织印花布疵点实时检测方法。通过优化骨干网络结构,引入可变形卷积,提高印花背景下模型的瑕疵特征提取能力;设计新的损失函数,提高瑕疵分类和定位的精准度;引入几何中位数剪枝算法,去除深层网络冗余参数,进一步提高系统检测速度。试验结果表明,改进算法的模型在测试集上准确率可达92.02%,检测精度显著提高,每张图片检测平均耗时22.61 ms,满足工厂的实时性要求。展开更多
目的探讨术前细胞角蛋白19片段(cytokeratin fragment 19,CYFRA21-1)联合癌胚抗原(carcinoembryonic antigen,CEA)检测对T2期非小细胞肺癌患者淋巴结转移的预测价值。方法回顾性分析2020年1月至2022年10月在首都医科大学附属北京胸科医...目的探讨术前细胞角蛋白19片段(cytokeratin fragment 19,CYFRA21-1)联合癌胚抗原(carcinoembryonic antigen,CEA)检测对T2期非小细胞肺癌患者淋巴结转移的预测价值。方法回顾性分析2020年1月至2022年10月在首都医科大学附属北京胸科医院接受手术治疗的448例T2期非小细胞肺癌患者的临床病理资料,根据术前肿瘤标志物CYFRA21-1、CEA的表达水平将其分为高表达组(CYFRA21-1≥6ng/ml或CEA≥6ng/ml,168例)和低表达组(CYFRA21-1<6ng/ml且CEA<6ng/ml,280例),比较两组患者的性别、年龄、吸烟史、病理类型、肿瘤大小及位置、淋巴结转移发生率和侵及程度。结果高表达组淋巴结转移发生率为51.19%(86/168),明显高于低表达组的28.21%(79/280),差异有显著性(P<0.001)。进一步分析显示肿瘤标志物高表达率在N2组为54.74%(52/95),N1组为48.57%(34/70),N0组为28.98%(82/283),不同淋巴结侵及程度组间比较差异均有显著性(P<0.001)。结论CYFRA21-1和CEA表达水平与T2期非小细胞肺癌淋巴结转移的发生率和侵及程度相关,术前检测CYFRA21-1和CEA可评估T2期非小细胞肺癌患者的淋巴结转移风险,对术中有针对性的淋巴结清扫及术后优化辅助治疗具有重要的参考价值。展开更多
The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly...The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly affected by background patterns and are difficult to effectively extract flaw features.Therefore,a convolutional neural network(CNN)with automatic feature extraction is proposed.On the basis of the two-stage detection model Faster R-CNN,Resnet-50 is used as the backbone network,and the problem of flaws with extreme aspect ratio is solved by improving the initialization algorithm of the prior frame aspect ratio,and the improved multi-scale model is designed to improve detection of small defects.The cascade R-CNN is introduced to improve the accuracy of defect detection,and the online hard example mining(OHEM)algorithm is used to strengthen the learning of hard samples to reduce the interference of complex backgrounds on the defect detection of patterned fabrics,and construct the focal loss as a loss function to reduce the impact of sample imbalance.In order to verify the effectiveness of the improved algorithm,a defect detection comparison experiment was set up.The experimental results show that the accuracy of the defect detection algorithm of patterned fabrics in this paper can reach 95.7%,and it can accurately locate the defect location and meet the actual needs of the factory.展开更多
文摘针对布匹瑕疵自动化检测,基于传统的机器视觉方法依赖于人工设计特征,对具有复杂背景图案的花色布瑕疵特征提取难度非常大,因此提出一种基于改进Faster R-CNN(faster region with convolutional neural network)的花色布瑕疵检测算法。在Faster R-CNN的基础上使用Resnet-50作为主干网络,嵌入可变形卷积来提高瑕疵特征的学习能力。通过设计多尺度模型来提高小瑕疵的检测,引入级联网络来提高瑕疵检测精度和定位准确度,构造优化的损失函数来降低样本不平衡影响。通过试验验证了该算法的有效性。结果表明,瑕疵检测效果准确率达94.97%,并能精准定位瑕疵位置,可满足工厂的实际需求。
文摘为满足纺织业内机织印花布瑕疵检测的实时性需求,基于利用回归思想进行检测的单阶段算法模型YOLOv_(3)(you only look once version 3),提出一种改进的机织印花布疵点实时检测方法。通过优化骨干网络结构,引入可变形卷积,提高印花背景下模型的瑕疵特征提取能力;设计新的损失函数,提高瑕疵分类和定位的精准度;引入几何中位数剪枝算法,去除深层网络冗余参数,进一步提高系统检测速度。试验结果表明,改进算法的模型在测试集上准确率可达92.02%,检测精度显著提高,每张图片检测平均耗时22.61 ms,满足工厂的实时性要求。
文摘目的探讨术前细胞角蛋白19片段(cytokeratin fragment 19,CYFRA21-1)联合癌胚抗原(carcinoembryonic antigen,CEA)检测对T2期非小细胞肺癌患者淋巴结转移的预测价值。方法回顾性分析2020年1月至2022年10月在首都医科大学附属北京胸科医院接受手术治疗的448例T2期非小细胞肺癌患者的临床病理资料,根据术前肿瘤标志物CYFRA21-1、CEA的表达水平将其分为高表达组(CYFRA21-1≥6ng/ml或CEA≥6ng/ml,168例)和低表达组(CYFRA21-1<6ng/ml且CEA<6ng/ml,280例),比较两组患者的性别、年龄、吸烟史、病理类型、肿瘤大小及位置、淋巴结转移发生率和侵及程度。结果高表达组淋巴结转移发生率为51.19%(86/168),明显高于低表达组的28.21%(79/280),差异有显著性(P<0.001)。进一步分析显示肿瘤标志物高表达率在N2组为54.74%(52/95),N1组为48.57%(34/70),N0组为28.98%(82/283),不同淋巴结侵及程度组间比较差异均有显著性(P<0.001)。结论CYFRA21-1和CEA表达水平与T2期非小细胞肺癌淋巴结转移的发生率和侵及程度相关,术前检测CYFRA21-1和CEA可评估T2期非小细胞肺癌患者的淋巴结转移风险,对术中有针对性的淋巴结清扫及术后优化辅助治疗具有重要的参考价值。
基金National Key Research and Development Project,China(No.2018YFB1308800)。
文摘The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly affected by background patterns and are difficult to effectively extract flaw features.Therefore,a convolutional neural network(CNN)with automatic feature extraction is proposed.On the basis of the two-stage detection model Faster R-CNN,Resnet-50 is used as the backbone network,and the problem of flaws with extreme aspect ratio is solved by improving the initialization algorithm of the prior frame aspect ratio,and the improved multi-scale model is designed to improve detection of small defects.The cascade R-CNN is introduced to improve the accuracy of defect detection,and the online hard example mining(OHEM)algorithm is used to strengthen the learning of hard samples to reduce the interference of complex backgrounds on the defect detection of patterned fabrics,and construct the focal loss as a loss function to reduce the impact of sample imbalance.In order to verify the effectiveness of the improved algorithm,a defect detection comparison experiment was set up.The experimental results show that the accuracy of the defect detection algorithm of patterned fabrics in this paper can reach 95.7%,and it can accurately locate the defect location and meet the actual needs of the factory.
