Image processing apparatus, machine learning device, and image processing method
An image processing apparatus includes: a memory configured to store a machine-learned model produced by performing machine learning using teaching data associating image data generated by reading a document by an image reading device with device abnormality information on abnormality of the image reading device; and when the image reading device reads a document, a processor configured to obtain the device abnormality information based on generated image data and the machine-learned model.
1. An image processing apparatus comprising:
a memory configured to store a machine-learned model produced by performing machine learning using teaching data associating image data generated by reading a document by an image reading device with device abnormality information on abnormality of the image reading device; and
when the image reading device reads a document, a processor configured to determine whether a device abnormality associated with the image reading device is present based on generated image data and the machine-learned model.
2. The image processing apparatus according to claim 1 , wherein
in the teaching data, at least one of use history of the image reading device, reading resolution of a document, and a type of document medium is associated with the device abnormality information.
3. The image processing apparatus according to claim 2 , wherein
the use history includes at least one of replacement history of a document transport roller, history of document transport error, and transition information of a length variation value representing a difference between a number of pixels of a document in a sub scanning direction corresponding to a reading resolution and a number of pixels of generated image data in the sub scanning direction, and
the device abnormality information includes time when replacement of a document transport roller becomes necessary.
4. The image processing apparatus according to claim 3 , wherein
when the device abnormality information is information on replacement of a document transport roller, the processor informs to encourage ordering a document transport roller or automatically places an order.
5. The image processing apparatus according to claim 1 , wherein
the device abnormality information includes a handling method for abnormality, and
the handling method includes at least one of replacement of a document transport roller, cleaning of a document transport roller, and image correction of the image data generated by the reading.
6. The image processing apparatus according to claim 1 , wherein
the device abnormality information includes an abnormal place of the image reading device.
7. A machine learning device comprising:
a controller configured to:
obtain teaching data associating image data generated by reading a document by an image reading device with device abnormality information on abnormality of the image reading device, and
perform machine learning on a model configured to input the image data and output the device abnormality information based on the teaching data, the device abnormality information indicating whether a device abnormality associated with the image reading device is present.
8. An image processing method comprising:
storing a machine-learned model obtained by performing machine learning using teaching data associating image data generated by reading a document by an image reading device with device abnormality information on abnormality of the image reading device, and
when the image reading device reads a document, determine whether a device abnormality associated with the image reading device is present based on generated image data and the machine-learned model.