Abstract: When a normal inspection and an inspection through deep learning processing is applicable, high inspection accuracy is obtained while reducing a processing time. The normal inspection processing is applied to a newly acquired inspection target image, the non-defective product determination or the defective product determination is confirmed for the inspection target image having the characteristic amount with which the non-defective product determination or the defective product determination is executable based on the characteristic amount within the inspection target image and the threshold for confirming the non-defective product determination or the threshold for confirming the defective product determination.

Abstract: When a normal inspection and an inspection through deep learning processing is applicable, high inspection accuracy is obtained while reducing a processing time. The normal inspection processing is applied to a newly acquired inspection target image, the non-defective product determination or the defective product determination is confirmed for the inspection target image having the characteristic amount with which the non-defective product determination or the defective product determination is executable based on the characteristic amount within the inspection target image and the threshold for confirming the non-defective product determination or the threshold for confirming the defective product determination.

Abstract: The image inspection device includes a reference height setting part configured to set a reference height as a reference of vibration component estimation, a vibration estimation part configured to estimate a vibration component in an inspection environment, based on the two-dimensional profile generated by the two-dimensional profile generation part and the reference height set by the reference height setting part, a profile correction part configured to remove, from the two-dimensional profile, the vibration component estimated by the vibration estimation part, a three-dimensional data generation part configured to generate three-dimensional data of the inspection object from a plurality of the two-dimensional profiles from which the vibration component is removed by the profile correction part, and an inspection part configured to conduct outer appearance inspection of the inspection object, based on the three-dimensional data generated by the three-dimensional data generation part.

Abstract: The three-dimensional image inspection device includes a composed image generation part configured to compose first three-dimensional data and second three-dimensional data, and generate a three-dimensional composed image having information in a height direction, a composition mode selection part configured to enable a first composition mode and a second composition mode to be selected, the first composition mode being a mode in which the three-dimensional composed image is generated, based on the three-dimensional data measured by both a first light projecting/receiving part and a second light projecting/receiving part with respect to respective pixels configuring the three-dimensional composed image, and the second composition mode being a mode in which the three-dimensional composed image is generated, based on the three-dimensional data measured by any one or both of the first light projecting/receiving part and the second light projecting/receiving part with respect to the respective pixels.

Abstract: A photometric processing part calculates a normal vector of a surface of a workpiece from a plurality of luminance images acquired by a camera in accordance with the photometric stereo method, and performs synthesis processing of synthesizing at least two images out of an inclination image made up of pixel values based on the normal vector calculated from the plurality of luminance images and at least one reduced image of the inclination image, to generate an inspection image showing a surface shape of the inspection target. In particular, a characteristic size setting part sets a characteristic size which is a parameter for giving weight to a component of a reduced image at the time of performing the synthesis processing. The photometric processing part can generate a different inspection image in accordance with the set characteristic size.

Abstract: The image inspection device includes a reference height setting part configured to set a reference height as a reference of vibration component estimation, a vibration estimation part configured to estimate a vibration component in an inspection environment, based on the two-dimensional profile generated by the two-dimensional profile generation part and the reference height set by the reference height setting part, a profile correction part configured to remove, from the two-dimensional profile, the vibration component estimated by the vibration estimation part, a three-dimensional data generation part configured to generate three-dimensional data of the inspection object from a plurality of the two-dimensional profiles from which the vibration component is removed by the profile correction part, and an inspection part configured to conduct outer appearance inspection of the inspection object, based on the three-dimensional data generated by the three-dimensional data generation part.

Abstract: The three-dimensional image inspection device includes a composed image generation part configured to compose first three-dimensional data and second three-dimensional data, and generate a three-dimensional composed image having information in a height direction, a composition mode selection part configured to enable a first composition mode and a second composition mode to be selected, the first composition mode being a mode in which the three-dimensional composed image is generated, based on the three-dimensional data measured by both a first light projecting/receiving part and a second light projecting/receiving part with respect to respective pixels configuring the three-dimensional composed image, and the second composition mode being a mode in which the three-dimensional composed image is generated, based on the three-dimensional data measured by any one or both of the first light projecting/receiving part and the second light projecting/receiving part with respect to the respective pixels.

Abstract: A photometric processing part calculates a normal vector of a surface of a workpiece from a plurality of luminance images acquired by a camera in accordance with the photometric stereo method, and performs synthesis processing of synthesizing at least two images out of an inclination image made up of pixel values based on the normal vector calculated from the plurality of luminance images and at least one reduced image of the inclination image, to generate an inspection image showing a surface shape of the inspection target. In particular, a characteristic size setting part sets a characteristic size which is a parameter for giving weight to a component of a reduced image at the time of performing the synthesis processing. The photometric processing part can generate a different inspection image in accordance with the set characteristic size.

Abstract: A photometric processing part calculates a normal vector of a surface of a workpiece from a plurality of luminance images acquired by a camera in accordance with the photometric stereo method, and performs synthesis processing of synthesizing at least two images out of an inclination image made up of pixel values based on the normal vector calculated from the plurality of luminance images and at least one reduced image of the inclination image, to generate an inspection image showing a surface shape of the inspection target. In particular, a characteristic size setting part sets a characteristic size which is a parameter for giving weight to a component of a reduced image at the time of performing the synthesis processing. The photometric processing part can generate a different inspection image in accordance with the set characteristic size.

Abstract: A photometric processing part calculates a normal vector of a surface of a workpiece from a plurality of luminance images acquired by a camera in accordance with the photometric stereo method, and performs synthesis processing of synthesizing at least two images out of an inclination image made up of pixel values based on the normal vector calculated from the plurality of luminance images and at least one reduced image of the inclination image, to generate an inspection image showing a surface shape of the inspection target. In particular, a characteristic size setting part sets a characteristic size which is a parameter for giving weight to a component of a reduced image at the time of performing the synthesis processing. The photometric processing part can generate a different inspection image in accordance with the set characteristic size.