| 刘韵婷,刘 鑫,高 宇.基于 FAMGAN 的轮胎 X 光图像缺陷检测[J].电子测量与仪器学报,2023,37(12):58-66 |
| 基于 FAMGAN 的轮胎 X 光图像缺陷检测 |
| Defect detection of tire X-ray images based on FAMGAN |
| |
| DOI： |
| 中文关键词: 生成对抗网络 CBAM 深度学习 AFF 轮胎图像缺陷检测 JPU |
| 英文关键词:generative adversarial network CBAM deep learning AFF tire image defect detection JPU |
| 基金项目:辽宁省自然科学基金(2022-KF-14-02)、辽宁省教育厅面上项目(LJKMZ20220617)资助 |
|
|
|
|
| 摘要点击次数: 681 |
| 全文下载次数: 835 |
| 中文摘要: |
| 针对气泡缺陷特征和图像背景像素差异较小、检测困难的问题,以 Skip-GANomaly 为基础框架,提出了融合注意力机制
生成对抗网络(FAMGAN),首先,生成器中编码器和解码器之间的跳连层由注意力特征融合模块(AFF) 和注意力机制模块
(CBAM)构成,提高了对目标特征的关注、减少了图像特征丢失;然后,在判别器中加入联合上采样模块( JPU),提高了模型检
测图像缺陷的速度。 最后,将本文提出的 FAMGAN 网络与近几年经典的生成对抗网络在自制的轮胎缺陷数据集上进行训练、
测试和评估。 实验结果表明,本文提出的网络对轮胎气泡缺陷检测的精度达到 0. 837,相比于 Skip-GANomaly 网络提高了
近 30%。 |
| 英文摘要: |
| In response to the problem of small differences in blister defect features and background pixels in tire defect images, as well
as difficulty in detection, Skip-GANomaly is adopted as the basic framework to propose the fusion attention mechanism generative
adversarial network (FAMGAN). Firstly, the skip layer between the encoder and decoder in the generator consists of an attention feature
fusion (AFF) module and a convolutional block attention module (CBAM) module, which improves the focus on target features and
reduces image feature loss. Then, a joint pyramid upsampling (JPU) module was added to the discriminator to improve the speed of the
model in detecting image defects. Finally, the FAMGAN network proposed in this article will be trained, tested, and evaluated on a selfmade tire defect dataset with classic generative adversarial networks in recent years. The experimental results show that the proposed
network achieves an accuracy of 0. 837 for tire blister defect detection, which is nearly 30 percentage points higher than the Skip
GANomaly network. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
