[1]李文俊,胡 泓,李峥嵘.一种用于引线键合视觉定位的图像质量评估方法[J].机械与电子,2021,(03):60-64.
　LI Wenjun,HU Hong,LI Zhengrong.An Image Quality Assessment Method for Visual Positioning of Wire Bonder[J].Machinery & Electronics,2021,(03):60-64.
点击复制

一种用于引线键合视觉定位的图像质量评估方法()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2021年03期
页码:
60-64
栏目:
智能工程
出版日期:
2021-03-24

文章信息/Info

Title:
An Image Quality Assessment Method for Visual Positioning of Wire Bonder
文章编号:
1001-2257（2021）03-0060-05
作者:
李文俊; 胡 泓; 李峥嵘

1.哈尔滨工业大学（深圳）机电工程与自动化学院，广东 深圳 518000；

2.深圳市大族光电设备有限公司，广东 深圳 518000

Author(s):
LI Wenjun; HU Hong; LI Zhengrong

1.School of Mechanical Engineering and Automation, Harbin Institute of Technology,Shenzhen 518000,China

2.Han’s Laser Technology Industry Group Co.,Ltd.,Shenzhen 518000,China

关键词:
引线键合; 图像质量评估; 视觉定位; 图像生成
Keywords:
wire bonding;  image quality assessment;  visual positioning;  image generation
分类号:
TP391
文献标志码:
A
摘要:
引线键合机视觉定位的精度受到采集图像质量的影响，当采集图片的质量较差时，会导致定位精度发生较大的缺失。为了解决这个问题，将基于生成对抗网络的图片质量评估方案引入到引线键合机视觉系统中，作为引线键合机的“第三方监督者”对视觉系统采集到的图片质量进行实时监督，保证采集到的图片质量符合视觉定位需求，进而保障生产过程中引线键合的视觉定位精度。
Abstract:
The accuracy of the visual positioning of the wire bonder is affected by the quality of the collected images. When the quality of the collected images is poor, the positioning accuracy will be largely missing. In order to solve this problem, the image quality assessment based on generative adversarial networks is introduced into the vision system of the wire bonder to be the “third-party supervisor” of the wire bonder and the quality of the pictures collected by the vision system were monitored in real time to ensure that the quality of the collected pictures is consistent,and guarantee the visual positioning accuracy of lead welding during the production process.

参考文献/References:

[1]WANG Z, BOVIK A C, SHEIKH H R,et al.Image quality assessment: from error visibility to structural similarity[J].IEEE Transactions on image processing,2004,13(4):600–612.

[2]ZHANG L,ZHANG L,MOU X Q,et al. FSIM: A feature similarity index for image quality assessment[J]. IEEE Transactions on image processing,2011,20(8):2378-2386.

[3]KANG L,YE P,LI Y,et al.Convolutional neural networks for no-reference image quality assessment[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition,2014:1733-1740.

[4]BOSSE S,MANIRY D,MÜLLER K R,et al.Deep neural networks for no-reference and full-reference image quality assessment[J]. IEEE Transactions on image processing,2018,27(1):206-219.

[5]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Advances in Neural Information Processing Systems,2014:2672–2680.

[6]GULRAJANI I,AHMED F,ARJOVSKY M,et al.Improved training of Wasserstein GANs[C]//Advances in Neural Information Processing Systems, 2017:5767-5777.

[7]LEDIG C,THEIS L,HUSZAR F,et al.Photo-Realistic single image super-resolution using a generative adversarial network[C]//Computer Vision and Pattern Recognition, 2016:105-114.

[8]REN H Y, CHEN D Q, WANG Y Z.RAN4IQA: Restorative adversarial nets for no-reference image quality assessment[C]//Association for the Advancement of Artificial Intelligence,2018:7308-7314.

[9]LIN K Y , WANG G X. Hallucinated-IQA: no-reference image quality assessment via adversarial learning[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:732-741.

[10]JOHNSON J,ALAHI A,LI F F.Perceptual losses for real-time style transfer and super-resolution[C]//European Conference on Computer Vision(ECCV).Cham:Springer, 2016:694-711.

[11]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE,2014:770-778.

备注/Memo

备注/Memo:
收稿日期：2020-10-24

作者简介：李文俊(1993-)，男，硕士，湖北天门人，研究方向为视觉定位、图像生成和图像质量评价；胡泓(1965-)，男，博士，教授，博士研究生导师，研究方向为微机电系统(MEMS)、微流控制技术与精密仪器、线性、非线性控制系统理论、机电一体化系统与智能系统；李峥嵘（1975-），男，博士，研究方向为信号处理和运动控制。

更新日期/Last Update: 2021-03-22