Share Email Print
cover

Proceedings Paper

Fabric defect detection based on faster R-CNN
Author(s): Zhoufeng Liu; Xianghui Liu; Chunlei Li; Bicao Li; Baorui Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In order to effectively detect the defects for fabric image with complex texture, this paper proposed a novel detection algorithm based on an end-to-end convolutional neural network. First, the proposal regions are generated by RPN (regional proposal Network). Then, Fast Region-based Convolutional Network method (Fast R-CNN) is adopted to determine whether the proposal regions extracted by RPN is a defect or not. Finally, Soft-NMS (non-maximum suppression) and data augmentation strategies are utilized to improve the detection precision. Experimental results demonstrate that the proposed method can locate the fabric defect region with higher accuracy compared with the state-of- art, and has better adaptability to all kinds of the fabric image.

Paper Details

Date Published: 10 April 2018
PDF: 9 pages
Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106150A (10 April 2018); doi: 10.1117/12.2303713
Show Author Affiliations
Zhoufeng Liu, Zhongyuan Univ. of Technology (China)
Xianghui Liu, Zhongyuan Univ. of Technology (China)
Chunlei Li, Zhongyuan Univ. of Technology (China)
Bicao Li, Zhongyuan Univ. of Technology (China)
Baorui Wang, Zhongyuan Univ. of Technology (China)


Published in SPIE Proceedings Vol. 10615:
Ninth International Conference on Graphic and Image Processing (ICGIP 2017)
Hui Yu; Junyu Dong, Editor(s)

© SPIE. Terms of Use
Back to Top