Abstract
The evaluation of yarn surface appearance is an important routine in assessing yarn quality in textile industry. Traditionally, this evaluation is subjectively carried out by manual inspection, which is much skill-oriented, judgmental and inconsistent. To resolve the drawbacks of the manual method, an integrated intelligent characterization and evaluation model is proposed in this paper for the evaluation of yarn surface appearance. In the proposed model, attention-driven fault detection, wavelet texture analysis and statistical measurement are developed and incorporated to fully extract the characteristic features of yarn surface appearance from images and a fuzzy ARTMAP neural network is employed to classify and grade yarn surface qualities based on the extracted features. Experimental results on a database of 576 yarn images show the proposed intelligent evaluation system achieves a satisfactory performance both for the individual yarn category and global yarn database. In addition, a comparative study among the fuzzy ARTMAP, Back-Propagation (BP) neural network, and Support Vector Machine (SVM) shows the superior capacity of the proposed fuzzy ARTMAP in classifying yarn surface qualities of the database.
Original language | English |
---|---|
Pages (from-to) | 4201-4212 |
Number of pages | 12 |
Journal | Expert Systems with Applications |
Volume | 39 |
Issue number | 4 |
DOIs | |
Publication status | Published - 1 Mar 2012 |
Keywords
- Fuzzy ARTMAP neural network
- Saliency map
- Wavelet transform
- Yarn evaluation
- Yarn grading
ASJC Scopus subject areas
- General Engineering
- Computer Science Applications
- Artificial Intelligence