Automatic profiled fiber identification based on a sequential clustering algorithm

Automatic profiled fiber identification is of very significance to textiles quality control and performance design. In this paper, we present a facile sequential clustering algorithm used for profiled fiber identification. This clustering algorithm is based on dissimilarity measures between feature vectors. One of its advantages is that the final result is independent on the order in which the vectors are presented to the algorithm. Our profiled fiber identification system employs a feature extracting technique that uses the shape information residing in the boundary curve of profiled fiber cross-sections. The experimental results show that the defined shape descriptor and the classification method can effectively identify solid profiled fibers that differ in their cross sectional shapes.