Three-Dimensional Model Reconstruction of Nonwovens from Multi-Focus Images  

作　　者：DONG Gaige WANG Rongwu LI Chengzu YOU Xiangyin 董改革;王荣武;李成族;尤祥银

机构地区：[1]College of Textiles, Donghua University, Shanghai 201620, China [2]Jiangsu Liyang New Material Co. , Ltd. , Nantong 226004, China

出　　处：《Journal of Donghua University(English Edition)》2022年第3期185-192,共8页东华大学学报（英文版）

基　　金：National Natural Science Foundation of China(No.61771123)。

摘　　要：The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based on deep learning was proposed to reconstruct 3D models of nonwovens from multi-focus images.A convolutional neural network was trained to extract clear fibers from sequence images.Image processing algorithms were used to obtain the radius,the central axis,and depth information of fibers from the extraction results.Based on this information,3D models were built in 3D space.Furthermore,self-developed algorithms optimized the central axis and depth of fibers,which made fibers more realistic and continuous.The method with lower cost could reconstruct 3D models of nonwovens conveniently.

关 键 词：three-dimensional(3D)model reconstruction deep learning MICROSCOPY NONWOVEN image processing 

分 类 号：TS171[轻工技术与工程—纺织材料与纺织品设计]