Aiming at the problem that back propagation(BP)neural network predicts the low accuracy rate of fluff fabric after fluffing process,a BP neural network model optimized by particle swarm optimization(PSO)algorithm is p...Aiming at the problem that back propagation(BP)neural network predicts the low accuracy rate of fluff fabric after fluffing process,a BP neural network model optimized by particle swarm optimization(PSO)algorithm is proposed.The sliced image is obtained by the principle of light-cutting imaging.The fluffy region of the adaptive image segmentation is extracted by the Freeman chain code principle.The upper edge coordinate information of the fabric is subjected to one-dimensional discrete wavelet decomposition to obtain high frequency information and low frequency information.After comparison and analysis,the BP neural network was trained by high frequency information,and the PSO algorithm was used to optimize the BP neural network.The optimized BP neural network has better weights and thresholds.The experimental results show that the accuracy of the optimized BP neural network after applying high-frequency information training is 97.96%,which is 3.79%higher than that of the unoptimized BP neural network,and has higher detection accuracy.展开更多
In order to improve the accuracy of using visual methods to detect the quality of fluff fabrics,based on the previous research,this paper proposes a method of rapid classification detection using support vector machin...In order to improve the accuracy of using visual methods to detect the quality of fluff fabrics,based on the previous research,this paper proposes a method of rapid classification detection using support vector machine(SVM).The fabric image is acquired by the principle of light-cut imaging,and the region of interest is extracted by the method of grayscale horizontal projection.The obtained coordinates of the upper edge of the fabric are decomposed into high frequency information and low frequency information by wavelet transform,and the high frequency information is used as a data set for training.After experimental comparison and analysis,the detection rate of the SVM method proposed in this paper is higher than the previously proposed back propagation(BP)neural network and particle swarm optimization BP(PSO-BP)neural network detection methods,and the accuracy rate can reach 99.41%,which can meet the needs of industrial testing.展开更多
基金Natural Science Basic Research Plan in Shaanxi Province of China(No.2017JM5141)Shaanxi Provincial Education Department,China(No.17JK0334)+2 种基金Xi’an Polytechnic University Graduate Innovation Fund,China(No.chx2019083)Xi’an Science and Technology Bureau for Research Plan,China(No.201805030YD8CG14(5))Science Foundation for Doctorate Research of Xi’an Polytechnic University,China(No.BS1535)
文摘Aiming at the problem that back propagation(BP)neural network predicts the low accuracy rate of fluff fabric after fluffing process,a BP neural network model optimized by particle swarm optimization(PSO)algorithm is proposed.The sliced image is obtained by the principle of light-cutting imaging.The fluffy region of the adaptive image segmentation is extracted by the Freeman chain code principle.The upper edge coordinate information of the fabric is subjected to one-dimensional discrete wavelet decomposition to obtain high frequency information and low frequency information.After comparison and analysis,the BP neural network was trained by high frequency information,and the PSO algorithm was used to optimize the BP neural network.The optimized BP neural network has better weights and thresholds.The experimental results show that the accuracy of the optimized BP neural network after applying high-frequency information training is 97.96%,which is 3.79%higher than that of the unoptimized BP neural network,and has higher detection accuracy.
基金National Natural Science Foundation of China(No.61701384)Natural Science Basic Research Plan in Shaanxi Province of China(No.2017JM5141)+5 种基金Shaanxi Provincial Education Department,China(No.17JK0334)Xi'an Polytechnic University Graduate Innovation Fund,China(No.chx2019083)Science Foundation for Doctorate Research of Xi'an Polytechnic University,China(No.BS1535)Key Research and Development Program of Shaanxi,China(No.2020GY-172)Technology Innovation Leading Program of Xi'an,China(No.201805030YD8CG14(5))Xi'an Key Laboratory of Modern Intelligent Textile Equipment,China(No.2019220614SYS021CG043)。
文摘In order to improve the accuracy of using visual methods to detect the quality of fluff fabrics,based on the previous research,this paper proposes a method of rapid classification detection using support vector machine(SVM).The fabric image is acquired by the principle of light-cut imaging,and the region of interest is extracted by the method of grayscale horizontal projection.The obtained coordinates of the upper edge of the fabric are decomposed into high frequency information and low frequency information by wavelet transform,and the high frequency information is used as a data set for training.After experimental comparison and analysis,the detection rate of the SVM method proposed in this paper is higher than the previously proposed back propagation(BP)neural network and particle swarm optimization BP(PSO-BP)neural network detection methods,and the accuracy rate can reach 99.41%,which can meet the needs of industrial testing.
