Automatic Defect Segmentation in X-Ray Images Based on Deep Learning

doi:10.1109/TIE.2020.3047060

2021-12-01

PRE

Wangzhe Du

Jianzhong Fu

DOI：10.1109/TIE.2020.3047060

原文链接

原文求助

摘要

En 中文

X-ray imaging has been broadly adopted as a nondestructive testing method for product quality inspection. Deep learning has demonstrated powerful image scene understanding capabilities. In this article, U-Net with resnet101 is taken as the baseline for defect segmentation. First, there exist gray inhomogeneous and low-contrast regions in X-ray images, which can hardly be segmented. Contrast-limited adaptive histogram equalization (CLAHE) could be used to improve the contrast and consistency of the X-ray image. A two-stream convolutional neural network (CNN) is proposed that takes the original image and CLAHE processed image as inputs to address this issue. And then in CNN, low-level feature maps are lacking semantic information, which may lead to worse results. A gated multilayer fusion module is proposed to adaptively fuse the high-level features into low-level features. Furthermore, loss functions (such as cross entropy) in semantic segmentation are usually pixel level, ignoring the regional information. A weighted intersection over union (IOU) loss function is proposed to introduce IOU information to guide the model to focus on the objects that are easy to mine. The experimental results prove that the three proposed methods have better performance than the baseline for our dataset, achieving 42.2 in mIoU, 59.2 in Dice, and 54.5%, 74.9%, and 86.3% in small, middle, and large object recall rate, respectively.

Keyword:

Image segmentation

X-ray imaging

Feature extraction

Semantics

Deep learning

Object segmentation

Manufacturing

Casting parts

computer vision

deep learning

defect segmentation

nondestructive testing (NDT)

X-ray image

期刊

IEEE Transactions on Industrial Electronics

IF:

7.2

论文数:

1.8W

被引数:

9.8W

机构

zhejiang university

学者数:

17.7W

论文数: 12.1W

被引数: 152

引用论文

Efficacy of Ocrelizumab on Brain MRI Outcomes in Patients with Early Relapsing Multiple Sclerosis: Pooled Analysis of the OPERA Studies (P6.338)

Neurology

IF0

2017-04-18

PREAI

Anthony Traboulsee; Stephen Hauser; Eva Havrdova; Ludwig Kappos; Michael Racke; Krzysztof Selmaj; Shibeshih Belachew; Corrado Bernasconi; Regine Buffels; Hideki Garren; Wei Wei; Douglas Arnold

Domain Adaptation for Automatic OLED Panel Defect Detection Using Adaptive Support Vector Data Description

INTERNATIONAL JOURNAL OF COMPUTER VISION

IF9.3

2016-09-23

PREAI

Sindagi, Vishwanath A.; Srivastava, Sumit

Effects of acid concentration, temperature, and time on recycling of post-vehicle-application lithium-ion batteries of varying chemistries

Materials for Renewable and Sustainable Energy

IF0

2015-04-14