Fuzzy image processing in quality control application

Today, a visual inspection of the repair coating quality in can ends of metal containers for fish food is carried out. This visual inspection is a manual and non-destructive testing procedure. In order to improve this quality control, we have developed an automated inspection system, based on machine vision, which assesses the repair coating quality of each can end with a fuzzy system. In this work, the easy open can end manufacturing process, and the current, conventional method for quality control of easy open can end repair coating, are firstly described. After that, we show the fuzzy image processing to inspect each can end. Finally, results obtained and concluding remarks are stated. It is important to note the ability of the fuzzy model to favor the interpretability supplied to the operators in order to find out the failure causes and reduce mean time to repair during failures.