Journal of Textile Science & Engineering

ISSN: 2165-8064

Open Access

Fabric Weave Pattern Detection Based on Fuzzy Clustering and Texture Orientation Features in Wavelet Domain


Sulochan HC

Automatic fabric defect detection plays an important role in textile industry. In this paper, a novel weave pattern detection method based on multiscale wavelet features and fuzzy clustering approach is proposed to tackle the problem in automatic weave pattern detection of woven fabric. Fuzzy C-means (FCM) clusters the multiscale features of the crossed areas of the fabric into two clusters. The state of the crossed area is determined by texture orientation features. The weave pattern is detected using the crossed area states. Since the proposed detection scheme requires few features, the amount of computational load involved is not significant. Moreover, an error correction algorithm has been added to correct the detection errors in some crossed areas. The performance of the proposed method is validated with plain and twill fabric images.


Share this article

Google Scholar citation report
Citations: 1008

Journal of Textile Science & Engineering received 1008 citations as per Google Scholar report

Journal of Textile Science & Engineering peer review process verified at publons

Indexed In

arrow_upward arrow_upward