Research Article

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

Figure 7

Important part of 5 1 2 × 5 1 2 -pixel image of all types of defect. (a) For color yarn, 𝑊 D W = 4 2 p i x e l s . (b) For hole, 𝑊 D W = 3 3 p i x e l s . (c) For hole, 𝑊 D W = 1 2 7 p i x e l s . (d) For vertical missing yarn, 𝑊 D W = 3 3 p i x e l s . (e) For horizontal missing yarn, 𝑊 D W = 5 1 2 p i x e l s . (f) For spot, 𝑊 D W = 1 2 2 p i x e l s . (g) For spot, 𝑊 D W = 3 9 2 p i x e l s .
643473.fig.007a
(a)
643473.fig.007b
(b)
643473.fig.007c
(c)
643473.fig.007d
(d)
643473.fig.007e
(e)
643473.fig.007f
(f)
643473.fig.007g
(g)