计算机工程与应用2019，Vol.55Issue(6)：168-172,264,6.DOI:10.3778/j.issn.1002-8331.1712-0040
基于改进的R-FCN带纹理透明塑料裂痕检测
Textured Transparent Plastics Crack Detection Based on Improved R-FCN
摘要
Abstract
To solve the problem of the detection accuracy and recognition using traditional machine learning method to detect texture with transparent plastic crack rate is not high, an improved detection method based on Region-based Fully Convolutional Networks(R-FCN)is proposed. It makes up for the shortcomings of the original network’s low sensitivity to tiny cracks by using mixed-scale receptive field fusion procession in Residual Network(ResNet). Experimental results show that the crack detection accuracy based on improved R-FCN is about 20% higher than that based on Support Vector Machine (SVM), and is about 8% higher than that based on R-FCN without improvement. The validity of the method is proved.关键词
裂痕检测/支持向量机(SVM)/基于区域的全卷积网络(R-FCN)/残差网络(ResNet)/感受野Key words
crack detection/Support Vector Machine(SVM)/Region-based Fully Convolutional Networks(R-FCN)/Residual Network(ResNet)/receptive field分类
信息技术与安全科学引用本文复制引用
关日钊,陈新度,吴磊,徐焯基..基于改进的R-FCN带纹理透明塑料裂痕检测[J].计算机工程与应用,2019,55(6):168-172,264,6.基金项目
中国科学院先导培育项目(No.ZDBS16ZRJ1). （No.ZDBS16ZRJ1）
