Soft computing for automated surface quality analysis of exterior car body panels

Eichhorn, Andreas; Girimonte, Daniela; Klose, Aljoscha; Kruse, Rudolf

doi:10.1016/j.asoc.2004.08.002

Cited by 18 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Apart from surface models for inspection purposes, research effort has been put into defect classification with current focus on decision tree and rule based classification algorithms [17], [18].…”

Section: A Related Workmentioning

confidence: 99%

A Defect Recognition System for Automated Inspection of Non-rigid Surfaces

Enzberg¹,

Al-Hamadi²

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

The goal of this work is the automated recognition of 3D surface defects for quality inspection in industrial production. For complexly shaped workpieces that are non-rigid and have non-uniform tolerance ranges, it is hard to distinguish acceptable surface deviations from defects.We propose a 3-stage defect recognition system based on 3D measurement of the defective part. First, a variable B-Spline surface model is used to adapt to acceptable tolerance ranges. The remaining model deviations are then used for segmentation of possible defects. Finally, a SVM-based classifier separates true defects from pseudo defects.On a real world data set of a series of measurements for a car front hood, the effectiveness of the approach is proven.

show abstract

Section: A Related Workmentioning

confidence: 99%

A Defect Recognition System for Automated Inspection of Non-rigid Surfaces

Enzberg¹,

Al-Hamadi²

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…These decisions may often depend on the co-occurrence of several ROI on the same image, or on the repeated occurrence of ROI in similar positions on a sequence of images. ROI labelling in itself can be a problematic task due to the geometry of the defects being specified by vague terms and attributes resulting in variation in labelling by experts due to lack of objective criteria [9]. Changes to the rest of the system, i.e., the processes leading to the identification of ROI, require expert input in terms of image processing knowledge, to reliably isolate them from the background.…”

Section: Introductionmentioning

confidence: 99%

Adaptive surface inspection via interactive evolution

Caleb-Solly¹,

Smith²

2007

Image and Vision Computing

View full text Add to dashboard Cite

“…Outer panels are the most important parts for the perfect quality because outer panels are directly visible to the customer. In general, the impression of a car is determined by an appealing design of its body, the color and gloss of its paint, and the manufacturing and assembly accuracy of the exterior body panels [1].…”

Section: Introductionmentioning

confidence: 99%

Visualization of Subtle Defects of Car Body Outer Panels

Chung

Chang²

2006

2006 SICE-ICASE International Joint Conference

View full text Add to dashboard Cite

In the development of press dies especially for outer panels in the automotive industry, the cycle of the press panel inspection and the die modification process is about one month. Car body die makers are trying to reduce the inspection and modification cycle time. Defects of pressed panels are important inspection items for die makers. Subtle defects on un-painted panels are difficult to find and measure even for skilled workers. This paper presents a method to visualize the subtle defects of car body outer panels from the 3D scan data. First, curvature estimation methods for the 3D scan data are devised and experimented. Second, measures to find defect regions from the curvature map are also devised and verified. Several examples are presented.

show abstract

Soft computing for automated surface quality analysis of exterior car body panels

Cited by 18 publications

References 11 publications

A Defect Recognition System for Automated Inspection of Non-rigid Surfaces

A Defect Recognition System for Automated Inspection of Non-rigid Surfaces

Adaptive surface inspection via interactive evolution

Visualization of Subtle Defects of Car Body Outer Panels

Contact Info

Product

Resources

About