对于织物疵点的识别分类，本文设计了一个三层BP神经网络，经试验验证对六类织物图像的正确识别率可达95.83%。
For the part of identification of fabric defects, a three layer BP neural network is designed. After testing, six classes fabric image can be correctly identified by the rate of 95.83%.
用途：用于编织珊瑚绒、座垫等三层间隔织物。
Application: It is used to produce coral flannelette seat cushion and other sandwich fabric.
应用推荐