An inspection device of the present invention includes: THz wave irradiation unit for irradiating a specimen with THz waves; a THz wave sensing unit for detecting transmitted waves or reflected waves of the THz waves emitted to the specimen; and an information processing unit for acquiring intensity distribution of the transmitted waves of the reflected waves of the specimen from the intensity data of the transmitted waves or the reflected waves of the specimen irradiated with the THz waves, wherein the information processing unit acquires 2-dimensional intensity distribution of the transmitted waves or reflected waves, and detects whether a foreign matter is adhering to the specimen by comparing the intensity distribution obtained when the specimen without attachment of the foreign matter is detected and the intensity distribution obtained when the specimen is detected at the time of inspection. The specimen is a sheet of paper, for example.

A learned model generation method includes: using a teacher image including a defect map that is an image indicating a distribution of a defect portion of a surface of steel and having an equal image size, and presence/absence of periodic defects assigned in advance to the defect map; and generating a learned model by machine learning, the learned model for which: an input value is a defect map that is an image indicating a distribution of a defect portion of a surface of steel and having an image size of the equal image size; and an output value is a value concerning presence/absence of periodic defects in the defect map.

A learned model generation method includes: using a teacher image including a defect map that is an image indicating a distribution of a defect portion of a surface of steel and having an equal image size, and presence/absence of periodic defects assigned in advance to the defect map; and generating a learned model by machine learning, the learned model for which: an input value is a defect map that is an image indicating a distribution of a defect portion of a surface of steel and having an image size of the equal image size; and an output value is a value concerning presence/absence of periodic defects in the defect map.

A system, method, and apparatus for inspecting a label for proper application thereof. The system includes a label application apparatus and an inspection apparatus associated with said label application apparatus. The method includes inspecting a spent carrier web for the presence of labels, or portions thereof, that did not transfer to articles being labeled.

A system, method, and apparatus for inspecting a label for proper application thereof. The system includes a label application apparatus and an inspection apparatus associated with said label application apparatus. The method includes inspecting a spent carrier web for the presence of labels, or portions thereof, that did not transfer to articles being labeled.

A magnetic tape device (100) includes: a winding reel (101) winding a magnetic tape (201); a drive head (103) performing writing information onto the magnetic tape (201) and/or reading the information recorded on the magnetic tape (201); an image sensor (104) picking up an image of a surface of the magnetic tape (201); and a control unit (105) performing image processing on the image picked up the image sensor (104) and determining presence/absence of an abnormality on the surface of the magnetic tape (201), in which the control unit (105) adjusts, in accordance with at least either one of a type of the drive head (103) and a recording density of the magnetic tape (201), a winding speed at which the magnetic tape (201) is wound by the winding reel (101) when the image sensor (104) picks up the image of the surface of the magnetic tape (201).

A shape inspection apparatus includes N illumination light sources, a line sensor camera, a measurement control unit, and a data processing unit. The measurement control unit controls the illumination light sources to modulate luminescence intensities at a frequency that is 1/N of a frequency of a scan rate of the line sensor camera, and to emit lights by sequentially repeating N different patterns of illumination intensity ratios. The data processing unit generates a first separated image and a second separated image based on a photographed image, generates a first mixing elimination image acquired by removing an unnecessary illumination component from the first separated image, and a second mixing elimination image acquired by removing an unnecessary illumination component from the second separated image, and calculates an inclination of the surface of the strip-shaped body based on a difference between the first mixing elimination image and the second mixing elimination image.

A shape inspection apparatus includes N illumination light sources, a line sensor camera, a measurement control unit, and a data processing unit. The measurement control unit controls the illumination light sources to modulate luminescence intensities at a frequency that is 1/N of a frequency of a scan rate of the line sensor camera, and to emit lights by sequentially repeating N different patterns of illumination intensity ratios. The data processing unit generates a first separated image and a second separated image based on a photographed image, generates a first mixing elimination image acquired by removing an unnecessary illumination component from the first separated image, and a second mixing elimination image acquired by removing an unnecessary illumination component from the second separated image, and calculates an inclination of the surface of the strip-shaped body based on a difference between the first mixing elimination image and the second mixing elimination image.

Provided are a printed matter inspection device, a printed matter inspection method, a program, and a printing apparatus capable of suppressing erroneous detection in detection of a defect occurring in one direction. The printed matter inspection device and the printing apparatus include a print data acquisition unit that acquires print data, an imaging data acquisition unit that acquires imaging data of a printed matter, a registration processing unit that executes registration between the print data and the imaging data by applying a specified registration accuracy, and an inspection processing unit that acquires defect information of the imaging data based on the print data. A learning model that has been learned by using a disturbance-imparted learning data set having, as an input, disturbance-imparted imaging data in which a disturbance that shifts a position of the imaging data in a direction intersecting a relative transport direction between the printing section and the medium in the printing apparatus is imparted, and having defect information as an output is applied to the inspection processing unit.

In cutting a band-shaped glass film along a longitudinal direction thereof and evaluating linearity of an end side formed in association with the cutting to inspect quality of a cut band-shaped glass film, the following steps are performed: an imaging step of dividing the end side into a plurality of segments and imaging each of the plurality of segments; a linear approximation step of calculating an approximate straight line of the end side based on a plurality of points different from each other on the end side in each of a plurality of images obtained in the imaging step; a variation calculation step of calculating a variation value of the plurality of points based on the approximate straight line; and an evaluation step of evaluating the linearity of the end side based on a plurality of variation values respectively corresponding to the plurality of images.