Research Article

A Set of Geometric Features for Neural Network-Based Textile Defect Classification

Figure 6

Important part of 5 1 2 × 5 1 2 -pixel image of all types of defect. (a) For color yarn, 𝐻 D W = 2 9 p i x e l s . (b) For hole, 𝐻 D W = 3 6 p i x e l s . (c) For hole, 𝐻 D W = 8 7 p i x e l s . (d) For vertical missing yarn, 𝐻 D W = 5 1 2 p i x e l s . (e) For horizontal missing yarn, 𝐻 D W = 2 8 p i x e l s . (f) For spot, 𝐻 D W = 1 2 5 p i x e l s . (g) For spot, 𝐻 D W = 4 0 9 p i x e l s .
643473.fig.006a
(a)
643473.fig.006b
(b)
643473.fig.006c
(c)
643473.fig.006d
(d)
643473.fig.006e
(e)
643473.fig.006f
(f)
643473.fig.006g
(g)