Abstract

Repeating pattern recognition and extraction are important processes in the production and analysis of printed fabrics. In this study, the repeating patterns on printed fabric were extracted and innovatively analyzed using gray-scale image transform, two-dimensional discrete wavelet transform, fast Fourier transform and adaptive K-means clustering methods. The gray-scale image and two-dimensional discrete wavelet transforms were applied to compress the image. Image spectral characteristics were analyzed with a fast Fourier transform (FFT), the true fundamental frequency was extrapolated from its multiples, and frequency grouping was achieved using adaptive k-means clustering. The groups with the lowest frequencies in the image rows and columns were taken as giving the extraction frequency, and then the extraction frequency was mapped back onto the uncompressed fabric image to obtain the repeating pattern of the printed fabric. The similarity between patterns was used as a criterion for judging pattern design derivativeness. Similarity analysis was divided into two stages to reduce the calculation time and the amount of calculation required. In the first stage, repeating patterns were extracted and compared with existing patterns in an image database. In the second phase similarity analysis was carried out. The experimental results show the feasibility of the application of fast Fourier transforms to establishing a database of repeating patterns of printed fabrics. The average automatic repeated pattern extraction time is 10 s per image. The similarity analysis developed in the study has an accuracy rate of 98.0%, a sensitivity of 94.4% and a specificity of 98.5%. It is suitable for the analysis of all printing patterns, and meets the needs of the industry and printing pattern designers for data sharing and economical, competitive product management, over the total lifecycle of a fabric product from development to delivery, so satisfying market and societal needs.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call