Print medium specification method and print medium specification system

1 . A print medium specification method for specifying a type of a print medium, the method comprising:

(a) acquiring first physical property information related to the print medium;

(b) acquiring second physical property information different from the first physical property information related to the print medium, the second physical property information having a value for at least one type of information that is not included within the first physical property information, or the first physical property information having a value for at least one type of information that is not included within the second physical property information;

(c) acquiring discrimination information for discriminating the type of the print medium by inputting the first physical property information to a discrimination function configured as a learned machine learning model; and

(d) specifying a type of the print medium using the discrimination information and the second physical property information not used for machine learning.

2 . The print medium specification method according to claim 1 , wherein

the specifying includes

calculating a similarity for each type of the print medium using the second physical property information when the discrimination information indicates that the type of the print medium is undetermined and

specifying the type of the print medium by using the similarity.

3 . The print medium specification method according to claim 1 , wherein the discrimination information includes a first similarity for each type of the print medium and

the specifying includes

calculating a second similarity for each type of the print medium by using the second physical property information and

specifying a type of the print medium by using the first similarity and the second similarity.

4 . The print medium specification method according to claim 1 , wherein

the first physical property information and the second physical property information include at least one of a spectral reflectance, a spectral transmittance, a reflectance distribution, a captured image captured by a visible light camera, a thickness, an amount of water, a weight, a friction coefficient, and an ultrasonic inspection image.

5 . The print medium specification method according to claim 4 , wherein

the first physical property information is a spectral reflectance and

the second physical property information is the reflectance distribution including reflectance at a plurality of reflection angles with respect to one or more incident angle.

6 . A print medium specification method for specifying a type of a print medium, the method comprising:

(a) acquiring first physical property information related to the print medium;

(b) acquiring second physical property information different from the first physical property information related to the print medium;

(c) acquiring discrimination information for discriminating the type of the print medium by inputting the first physical property information to a discrimination function configured as a learned machine learning model; and

(d) specifying a type of the print medium using the discrimination information and the second physical property information not used for machine learning, wherein

the discrimination information includes a first similarity for each type of the print medium,

the specifying includes calculating a second similarity for each type of the print medium by using the second physical property information, and specifying a type of the print medium by using the first similarity and the second similarity,

the discrimination function includes a vector neural network having a plurality of vector neuron layers, and is configured so that a plurality of types of the print medium are divided into a plurality of classes, and

the first similarity is a similarity for each class calculated between a feature spectrum obtained from an output of a specific layer of the machine learning model and a known feature spectrum group created in advance in association with the plurality of classes.

7 . The print medium specification method according to claim 6 , wherein

the specific layer has a configuration in which vector neuron disposed on a plane defined by two axes of a first axis and a second axis is disposed as a plurality of channels along a third axis in a direction different from the two axes and

the feature spectrum is any one of the following:

(i) a first type of feature spectrum in which a plurality of element values of an output vector of a vector neuron at one plane position in the specific layers are arranged across the plurality of channels along the third axis,

(ii) a second type of feature spectrum obtained by multiplying each element value of the first type of feature spectrum by an activation value corresponding to a vector length of the output vector, and

(iii) a third type of feature spectrum in which the activation values at one plane position in the specific layers are arranged across the plurality of channels along the third axis.

8 . A print medium specification system for executes medium specification process for specifying a type of a print medium comprising:

a memory configured to store a discrimination function configured as a learned machine learning model and

a processor configured to execute the medium specification process by using the discrimination function, wherein

the processor is configured to perform the following process:

(a) process for acquiring first physical property information related to the print medium,

(b) process for acquiring second physical property information different from the first physical property information related to the print medium, the second physical property information having a value for at least one type of information that is not included within the first physical property information, or the first physical property information having a value for at least one type of information that is not included within the second physical property information,

(c) process for inputting the first physical property information to the discrimination function to acquire discrimination information for discriminating a type of the print medium,

(d) process for specifying the type of the print medium by using the discrimination information and the second physical property information, which is not used in machine learning.