Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models

Hansen, Anne Juhler; Knoche, Hendrik; Moeslund, Thomas B.

doi:10.1109/qomex.2018.8463295

Cited by 2 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We address our problem of quality inspection of premium products by evaluating different visual features in the context of brushed aluminium surfaces. As follows, we narrow our scope to visually perceived defects and more specifically line defects [2]. These include common defect types as scratches, polishing fish etc.…”

Section: Defect Appearance and Quality Standardsmentioning

confidence: 99%

“…This includes leveraging the current practice of assessors rotating objects and applying standard defect descriptors (location, size, shape etc.) [1], [2]. Current standards [6] are used for assessment of defect types within manual inspection but do not quantify the defect descriptors such than an automated system could use them to classify defects.…”

Section: Defect Appearance and Quality Standardsmentioning

confidence: 99%

“…The above approaches captured data from only a single viewpoint and lacked multi-view assessment of defects. Highly reflective materials, such as brushed aluminium surfaces, requires units to be inspected from various view angles [2]: a) for all unit surfaces in 3D (e.g. front and back sides) b) for defects only visible from certain view angles, and c) to account for specular reflections in the images.…”

Section: Automatic Visual Inspectionmentioning

confidence: 99%

“…Defects are defined based on visual descriptors and can be quantified and separated from design features due to irregularities in area, contrast, width, length, frequency etc. [2]. In their search for defects, human assessors rotate objects to probe different incoming illumination angles to make defects visible and compare them with design features [2].…”

Section: Introductionmentioning

confidence: 99%

“…[2]. In their search for defects, human assessors rotate objects to probe different incoming illumination angles to make defects visible and compare them with design features [2]. This technique is especially used when assessing reflective surfaces.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Defect or Design? Leveraging the Angle of Opportunity for Detecting Scratches on Brushed Aluminium Surfaces

2021

Self Cite

View full text Add to dashboard Cite

Design features such as polishing strokes share similarities with defects; this makes defect detection and quality assessment difficult to perform both manually and automatically. Human assessors rotate objects to probe different incoming illumination angles and evaluate the defect dimension to limits samples i.e. decide whether differences between defect candidates and design features qualify as a defect. This process has poor access to quantifiable defect descriptors needed for automation and expose a gap in the existing evaluation of defects. To integrate this notion into automated defect detection we propose a spatio-temporal image acquisition setup capturing the defect descriptor Angle of Opportunity (AoO) which can be used as a feature for image-based classification. The Random Forest approach classified defects with an area under the ROC-curve of 92%.

show abstract

Section: Defect Appearance and Quality Standardsmentioning

confidence: 99%

Section: Defect Appearance and Quality Standardsmentioning

confidence: 99%

Section: Automatic Visual Inspectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Defect or Design? Leveraging the Angle of Opportunity for Detecting Scratches on Brushed Aluminium Surfaces

2021

Self Cite

View full text Add to dashboard Cite

show abstract

Machine Vision for Aesthetic Quality Control of Reflective Surfaces

Hansen

Philipsen

Knoche

et al. 2021

Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2021)

Self Cite

View full text Add to dashboard Cite

Systems for automatic inspection of product quality are in high demand. However, their prevalence is limited by complex development and great expenses. Since inspection systems must be engineered to specific products and environments, such systems are generally only viable with high volume product series. Inspired by human visual inspection of highly reflective brushed aluminium objects we capture images across multiple viewpoints. We employ a spatio-temporal weighting of defects, where defects that occur consistently across viewpoints are considered more severe, and compare to the confidence scores produced by an off-the-shelf object detector (YOLOv5). Our results show the challenges with training object detectors on a realistic low-volume dataset of reflective brushed surfaces. Despite the poor detection performance and difficulty in distinguishing between design and defects, our method proves to classify our small test set with an area under the precision-recall curve of 66.5%.

show abstract

Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models

Cited by 2 publications

References 0 publications

Defect or Design? Leveraging the Angle of Opportunity for Detecting Scratches on Brushed Aluminium Surfaces

Defect or Design? Leveraging the Angle of Opportunity for Detecting Scratches on Brushed Aluminium Surfaces

Machine Vision for Aesthetic Quality Control of Reflective Surfaces

Contact Info

Product

Resources

About