id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_lccqoj5iyjfcpd4preqa64baum	Ma Xing	3D Target Recognition Based on Decision Layer Fusion	2018	4	.pdf	application/pdf	2584	236	53	3D Target Recognition Based on Decision Layer Fusion proposes a target recognition method based on decision layer point cloud data and multi-view images. used in the decision layer to complete the fusion of features. became a classical convolutional neural network image use the method of manually extracting features to classify convolutional neural networks to classify and recognize point cloud images, of which the VoxNet network has the vector machines require manually extracting image features Convolutional neural networks use local connections, weight The input layer are images, there are 5 convolutional convolutional layers, and the number of feature maps is 32, this paper uses the method of decision layer fusion. The feature fusion of the decision layer is usually the VoxNet using point cloud feature, and AlexNet is used to method with the recognition accuracy of VoxNet and neural network frameworks to extract point cloud features Convolutional Neural Networks for 3D Shape Recognition.	./cache/work_lccqoj5iyjfcpd4preqa64baum.pdf	./txt/work_lccqoj5iyjfcpd4preqa64baum.txt