An automatic fabric evaluation system has been developed to automatically a
nalyze the structure of woven fabric and objectively evaluate fabric qualit
y. Fabric images are captured by a CCD camera and preprocessed by Gaussian
filtering and histogram equalization. Fabric construction parameters such a
s count, cloth cover, yarn crimp, fabric thickness, and weight per unit are
a are measured automatically from planar and cross-sectional images of wove
n fabric with image processing and image analysis. Results obtained with th
e system show good correspondence with experimental values. In order to eva
luate the quality of woven fabric, defects such as slubs or missing picks a
re detected successfully from defect images, and the uniformity of yarn spa
cing and orthogonality of the yam intersecting angle are determined from no
rmal fabric images. The coefficients of variation of yarn spacing and the y
arn intersecting angle are measured quantitatively so that quality can be c
ompared using these values.