Abstract
Objective evaluation of smoothness appearance of fabrics after repeated home laundering is not only the key point, but also a difficulty in the field of textile inspection and clothing industry. This paper reports a 3D reconstruction system and method for objective assessment of fabric smoothness appearance based on Multi-view Stereo Vision (MVS) and Bag-of-Features (BOF). An image acquisition system for texture-less fabric was designed with a specific illumination module. Three-dimensional surface profile of wrinkled fabric was reconstructed by Structure from Motion (SFM) and Patch-based Multi-view Stereo (PMVS) techniques. To facilitate feature extraction, the generated 3D point cloud was mapped to a 2D image plane. The Bag-of-Features (BOF) model was utilized to characterize the fabric wrinkles and the K-Nearest Neighbor (KNN) algorithm was used to achieve automatic evaluation of fabric smoothness appearance. The experimental results with a high recognition of 93.33% indicated the effectiveness and stability of the proposed method.
Sign-in/Register to access full text options 
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
