Automatic Recognition of Fabric Weave Patterns by a Fuzzy C-Means Clustering Method

Sy‐Yen Kuo, Chung‐Yang Shih, Jiunn‐Yih Lee

Textile Research Journal · 2004 · 106 citations · 6 references

Concepts

TL;DR

The study proposes a robust algorithm for fabric weave pattern recognition. The method captures gray‑level scanner images of woven fabrics, enhances them, extracts texture features from warp‑weft interstices, and uses fuzzy c‑means clustering to classify warp and weft floats. Experiments show that the algorithm can clearly identify plain, twill, and satin weave patterns.

Abstract

A new robust recognition algorithm is proposed for fabric weave pattern recognition. The gray-level images of solid woven fabrics are captured by a color scanner and converted into digital files, then enhanced images are obtained by a gray-level morpho logical operation. Based on the interstices of yarns, warp and weft crossed areas are located, and four texture features of these areas are obtained by first-order and second- order statistics. Unsupervised decision rules for recognizing warp and weft floats are developed using a fuzzy c-means clustering method. The experimental materials include plain, twill, and satin woven fabrics. Experimental results demonstrate that three basic weave patterns can be clearly identified.

References

6