Quality grade recognition of knitted yarns by support vector machines

This paper presents the support vector machine (SVM) for classification of the quality grade of knitted yarns. The SVM, Kernel Fisher Discriminant Analysis (KFDA), back promulgation neural network (BPNN), and radial basis function neural network (RBFNN) are comparatively investigated in 94 classified knitted yarns from different mills in four-dimensional space, four methods are employed on IRIS and knitted yarns dataset, the experimental results exhibit SVM method has best classification effect. The FKCM method and the SVM method can constitute a complete quality evaluation system, and provide an objective evaluation method for knitted yarns quality.