Fantastic plastic? An Image-based Test Method to Detect Aesthetic Defects in Batches Based on Reference Samples

The production of high-end manufactured products requires Aesthetic Quality Control (AQC) in the form of human visual inspection.
Manufactures can reduce AQC costs by incorporating semi-automated visual defect detection in units with the existing 3D metrology scans.
This paper demonstrates how an image-based test method for defect detection can reduce the workload related to human visual inspection by proposing a median master comparison of batch image series. Our contribution consist of a) contrast enhancing and sorting batch image series for human visual inspection and b) providing a quality index (nQI) incorporated into statistical process control (SPC) for monitoring and controlling the AQC process. Our data shows that the median master differencing together with the nQI is great for classification of defects in batch images series. We introduce a SPC design proposal where individual batches as well as aggregated data can be inspected in synergy with the principles of Six Sigma. Based on Six Sigma control limits we have reduced the number of images in need of review by AQC assessors by a factor of 13.