Ryosuke Nakajima

A Study on the Effect of Inspection Time on Defect Detection in Visual Inspection

In order to consider the visual inspection utilizing the peripheral vision, this paper examines the inspection times that affect defect detection. The fixation duration and the distance between defect and the fixation point are experimental factors in determining the inspection time. As the result, in case of a large sized defect, the detection rate is high regardless of the fixation duration and the distance between the defect and the fixation point. In case of a small sized defect, when the fixation duration is longer and the distance between the defect and the fixation point is closer, the defect detection rate is higher. Moreover, as the result of conducting multiple linear regression analysis about the experiment factors, it is obtained that judging from standardized partial regression coefficient of factors, higher defect size, less the distance between defect and the fixation point, the higher fixation duration, is proved to improve the defect detection.

A Study on the Effect of Dirt on an Inspection Surface on Defect Detection in Visual Inspection Utilizing Peripheral Vision

This study focuses on adhered dirt to a product in production process, and also considers the relationship between dirt of inspection surface and defect detection in visual inspection utilizing peripheral vision. Specifically, images of inspection surface in an actual factory are analyzed using image analysis to do modeling. Moreover, dirt of inspection model, location and characteristics of defect are designed as experimental factors, and their effect on defect detection rate are evaluated. As a result, it is clarified that the defect detection rate becomes suddenly lower getting to the inspection surface dirtier. Consequently, defect that can be detected easily becomes harder to detect according as the inspection surface is dirtier.