Open AccessThe defect detection for X-ray images based on a new lightweight semantic segmentation network
Author(s) -
Yi Xin,
AUTHOR_ID,
Peng Chen,
Zhen Zhang,
Xiao Liang
Publication year - 2022
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2022193
Subject(s) - segmentation , artificial intelligence , computer science , feature (linguistics) , computer vision , encoder , pattern recognition (psychology) , image (mathematics) , set (abstract data type) , image segmentation , factory (object oriented programming) , fuse (electrical) , engineering , philosophy , linguistics , programming language , operating system , electrical engineering
The tire factory mainly inspects tire quality through X-ray images. In this paper, an end-to-end lightweight semantic segmentation network is proposed to realize the error detection of bead toe. In the network, firstly, the texture feature of different regions of tire is extracted by an encoder. Then, we introduce a decoder to fuse the output feature of the encoder. As the dimension of the feature maps is reduced, the positions of bead toe in the X-ray image have been recorded. When evaluating the final segmentation effect, we propose a local mIoU(L-mIoU) index. The segmentation accuracy and reasoning speed of the network are verified on the tire X-ray image set. Specifically, for 512 $ \times $ 512 input images, we achieve 97.1% mIoU and 92.4% L-mIoU. Alternatively, the bead toe coordinates are calculated using only 1.0 s.