Back to Search Start Over

FocusDet: towards high-quality digital printing fabric defect detection.

Authors :
Su, Zebin
Lu, Yanjun
Wu, Jingwei
Zhang, Huanhuan
Li, Pengfei
Source :
Textile Research Journal; Dec2023, Vol. 93 Issue 23/24, p5237-5248, 12p
Publication Year :
2023

Abstract

Deep-learning models have been effectively applied to the fabric defect detection field, in which dilemmas still exist for further improving product quality. For the self-built digital printing fabric defect detection dataset, the dilemmas can be expressed in aspects. First, the existing detection models are more inclined to learn many shot categories (head classes) and directly ignore low shot categories (tail classes); Second, the sampled positive and negative anchors in each mini-batch are not equally important, therefore they should be unequally attended to according to their importance. To solve these problems, in this article, a high-quality model for digital printing fabric defect detection was proposed, termed FocusDet. Specially, we construct the model based on the Faster-RCNN framework with two well-designed modules: the balanced group softmax module and the importance-based sample reweighting module, which improve the detection accuracy. Experimental results demonstrate that our proposed model reaches state-of-the-art accuracy on COCO metrics compared with other advanced detection models in the digital printing fabric defect detection dataset. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
00405175
Volume :
93
Issue :
23/24
Database :
Complementary Index
Journal :
Textile Research Journal
Publication Type :
Academic Journal
Accession number :
173453067
Full Text :
https://doi.org/10.1177/00405175231196324