Convolutional Neural Network Based on Spatial Pyramid for Image Classification

作     者：Gaihua Wang Meng Lu Tao Li Guoliang Yuan Wenzhou Liu 

作者机构：Hubei Collaborative Innovation Centre for High-Efficiency Utilization of Solar Energy Hubei University of TechnologyWuhan 430068China School of Electrical and Electronic EngineeringHubei University of TechnologyWuhan 430068China 

出 版 物：《Journal of Beijing Institute of Technology》 (北京理工大学学报（英文版）)

年 卷 期：2018年第27卷第4期

页      面：630-636页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081002[工学-信号与信息处理] 

基　　金：Supported by the National Natural Science Foundation of China(61601176) the Science and Technology Foundation of Hubei Provincial Department of Education(Q20161405) 

主　　题：convolutional neural network multiscale feature extraction image classification 

摘      要：A novel convolutional neural network based on spatial pyramid for image classification is *** network exploits image features with spatial pyramid ***,it extracts global features from an original image,and then different layers of grids are utilized to extract feature maps from different convolutional *** by the spatial pyramid,the new network contains two parts,one of which is just like a standard convolutional neural network,composing of alternating convolutions and subsampling *** those convolution layers would be averagely pooled by the grid way to obtain feature maps,and then concatenated into a feature vector ***,those vectors are sequentially concatenated into a total feature vector as the last feature to the fully connection *** generated feature vector derives benefits from the classic and previous convolution layer,while the size of the grid adjusting the weight of the feature maps improves the recognition efficiency of the *** results demonstrate that this model improves the accuracy and applicability compared with the traditional model.