id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_dwgtwxbuv5frtgrviz2ypnjcqu	He Li	Research on the Tunnel Geological Radar Image Flaw Detection Based on CNN	2020	10	.pdf	application/pdf	4144	368	60	Research on the Tunnel Geological Radar Image Flaw fast, nondestructive, continuous detection, real-time imaging, an improved method of void defect detection based on Faster RCNN (Regional Convolutional Neural Network) is proposed Keywords-Tunnel Geological; Radar Image; Flaw Detection; Geological radar detection method[1-2] is the survey images generated by radar equipment one by deep learning, using convolutional neural network R proposed the regional convolutional neural network Faster RCNN model is directly applied to the tunnel Faster RCNN model to expand original data sets, geological radar image detection. reflected in the radar image as positive and anti-peak Convolutional Neural Networks (CNN) can use output feature graph) is generated by convolution with image (because the RPN network and Fast RCNN Fast RCNN is a separate training detection network. Analysis of GPR image features of tunnel lining defects. object detection with region proposal networks[J]. Application of convolution neural network in image 	./cache/work_dwgtwxbuv5frtgrviz2ypnjcqu.pdf	./txt/work_dwgtwxbuv5frtgrviz2ypnjcqu.txt