A Lightweight Appearance Quality Assessment System Based on Parallel Deep Learning for Painted Car Body

The appearance quality assessment based on defect inspection for painted car-body surfaces is an essential work to monitor and analyze the level of paint appearance quality. In the industrial application, there are some challenges, such as the huge and stereo skeleton of car bodies, a variety of irregular local surface areas, low visibility of defects due to tiny real size, and specular car-body surface. To overcome these problems, a lightweight online appearance quality assessment system (OAQAS) based on parallel deep learning is proposed, it includes two parts: 1) a vision inspection subsystem with distributed multi-camera image acquisition module and 2) an appearance quality evaluation subsystem (AQES) based on parallel TinyDefectRNet for evaluating the proposed painted surface grinding difficulty criteria. TinyDefectRNet is able to inspect relatively accurate defect size, although it is trained on a coarsely annotated data set. The OAQAS is implemented in an actual painting production line of a car factory, and the application results show that our OAQAS is far superior to the manual inspection in evaluation accuracy and time consumption. Moreover, our system is lightweight so that it is easy to be plugged into existing painting production lines without rebuilding or changing the inspection room.

[1]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Ben Glocker,et al.  Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels , 2019, MICCAI.

[3]  Mian Li,et al.  Automated surface inspection for steel products using computer vision approach. , 2017, Applied optics.

[4]  Lining Sun,et al.  Surface defect detection method for glass substrate using improved Otsu segmentation. , 2015, Applied optics.

[5]  Jun-Bao Li,et al.  An infrared small target detection algorithm based on high-speed local contrast method , 2016 .

[6]  Larry S. Davis,et al.  SNIPER: Efficient Multi-Scale Training , 2018, NeurIPS.

[7]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Minho Chang,et al.  Visualization of Subtle Defects of Car Body Outer Panels , 2006, 2006 SICE-ICASE International Joint Conference.

[9]  Josep Tornero,et al.  On the detection of defects on specular car body surfaces , 2017 .

[10]  Michael Heizmann,et al.  INSPECTION OF SPECULAR AND PARTIALLY SPECULAR SURFACES , 2009 .

[11]  Matti Pietikäinen,et al.  Deep Learning for Generic Object Detection: A Survey , 2018, International Journal of Computer Vision.

[12]  Wei Liu,et al.  DSSD : Deconvolutional Single Shot Detector , 2017, ArXiv.

[13]  Qijun Zhao,et al.  Point in, Box Out: Beyond Counting Persons in Crowds , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Sören Kammel,et al.  Inspection of specular and painted surfaces with centralized fusion techniques , 2006 .

[15]  N. H. C. Yung,et al.  Automated fabric defect detection - A review , 2011, Image Vis. Comput..

[16]  Farzad Towhidkhah,et al.  Car Body Paint Defect Inspection Using Rotation Invariant Measure of the Local Variance and One-Against-All Support Vector Machine , 2011, 2011 First International Conference on Informatics and Computational Intelligence.

[17]  Xindong Wu,et al.  Object Detection With Deep Learning: A Review , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[20]  Jianbo Yu,et al.  Wafer Map Defect Detection and Recognition Using Joint Local and Nonlocal Linear Discriminant Analysis , 2016, IEEE Transactions on Semiconductor Manufacturing.

[21]  Min Liu,et al.  A mobile vision inspection system for tiny defect detection on smooth car-body surfaces based on deep ensemble learning , 2019, Measurement Science and Technology.

[22]  Ali Borji,et al.  Salient object detection: A survey , 2014, Computational Visual Media.

[23]  Andreas Eichhorn,et al.  Soft computing for automated surface quality analysis of exterior car body panels , 2005, Appl. Soft Comput..

[24]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[25]  Christian Döring,et al.  Improved Classification of Surface Defects for Quality Control of Car Body Panels , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[26]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[27]  Pierre Payeur,et al.  Automated surface deformations detection and marking on automotive body panels , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[28]  Guangming Shi,et al.  Feature-fused SSD: fast detection for small objects , 2017, International Conference on Graphic and Image Processing.

[29]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  De Xu,et al.  Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks , 2018, Applied Sciences.

[31]  Venkatesh Saligrama,et al.  BING++: A Fast High Quality Object Proposal Generator at 100fps , 2015, ArXiv.

[32]  Sang Jun Lee,et al.  Vision-based surface defect inspection for thick steel plates , 2017 .

[33]  Min Liu,et al.  Riemannian Alternative Matrix Completion for Image-Based Flame Recognition , 2017, IEEE Transactions on Circuits and Systems for Video Technology.