Visual inspection of products with geometrical quality characteristics of known tolerances

Image analysis techniques are being increasingly used to automate industrial inspection. The manual activity of inspection could be subjective and highly dependent on the experience of human personnel. In a previous work, the authors presented two approaches utilizing image analysis to inspect products visually. The product is accepted or rejected based on its conformance to specified tolerances, where conformance is analogy measured through statistical indices like correlation and root mean square error. In this work, the authors introduce a novel visual inspection approach that can be used on line to test simultaneously multiple quality characteristics. The approach utilizes image processing tools to deal with the product image; and extract features of its geometrical characteristics. Based on tolerance bands of each characteristic, an index is experimentally developed to reflect the deviation of a quality characteristic dimension from its nominal value; and one can decide whether a characteristic complies with the pre-specified tolerance. Statistical analysis proved that there is a strong association between the developed indices and the deviations of quality characteristics from their target values. Linear regression models are proved to model these associations; and are used to give the corresponding indices’ values relative to the tolerance specifications. The developed approach is proved to give a good performance experimentally in detecting non-conforming products; and, in specific, the defect location(s).