Loading…
Nondestructive Identification of Knot Types in Hand-Made Carpet. Part I: Feature Extraction from Grey Images
Knot (pile) formation has a very important role in evaluation and rating of hand-made carpets. Visual identification of carpet structural elements is impossible even for expert people. This research presents a nondestructive method for recognition of carpet knotting structure. It is based on X-ray r...
Saved in:
Published in: | Journal of nondestructive evaluation 2009-06, Vol.28 (2), p.55-62 |
---|---|
Main Authors: | , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Knot (pile) formation has a very important role in evaluation and rating of hand-made carpets. Visual identification of carpet structural elements is impossible even for expert people. This research presents a nondestructive method for recognition of carpet knotting structure. It is based on X-ray radiography (mammography). Available X-ray beams create visible images from the internal structure of object in two dimensions. Primary radiological images are taken by radiography from hand-made carpets. They are then converted to structural recognizable images by employing different image processing techniques.
Considering that the 3-D structure of carpet is projected in 2-D images and understanding the effect of each structural element on the creation of X-ray images, common knot types (piles) including Farsi, Torky, Kaman-Shib, double Farsi, double Torky and double Kaman-Shib are considerably distinguishable. |
---|---|
ISSN: | 0195-9298 1573-4862 |
DOI: | 10.1007/s10921-009-0047-7 |