Convolutional Neural Network Based on Spatial Pyramid for Image Classification

• 作 者: Gaihua Wang Meng Lu Tao Li Guo
• 机 构: HubeiCollaborativeInnovationCentreforHigh-EfficiencyUtilizationofSolarEnergy,SchoolofElectricalandEl
• 出 处: 北京理工大学学报:英文版
• 发表日期: 2018年4期
• 关键词: convolutional NEURAL NETWORK multiscale FEATURE EXTRACTION IMAGE CLASSIFICATION
• 基金项目: the National Natural Science Foundation of China (61601176),the Science and Technology Foundation of Hubei Provincial Department of Education (Q20161405).

A novel convolutional neural network based on spatial pyramid for image classification is proposed.The network exploits image features with spatial pyramid representation.First,it extracts global features from an original image,and then different layers o