Information processing device, and determination method

A determination method performed by an information processing device, the determination method comprising:

• acquiring XYZ values being values corresponding to a recognition target region as an image region in an image obtained by photographing an object under first illumination and being values represented in an XYZ color model, a spectral distribution, spectral reflectance in a case of a perfect reflecting diffuser, and determination information indicating a correspondence relationship between Lab values being values in an L*a*b* color space and a color, and calculating Lab values as values corresponding to the recognition target region in the L*a*b* color space by using the XYZ values, the spectral distribution and the spectral reflectance in the case of the perfect reflecting diffuser;
• and
• determining color of the recognition target region by using the calculated Lab values and the determination information,
• wherein
• when the spectral distribution is generated, acquiring the XYZ values of a reference color and spectral reflectance of a spot in the reference color, the XYZ values of the reference color being calculated based on RGB values acquired from an image region of the reference color in the image obtained by photographing the object under the first illumination, and generating a spectral distribution model by using principal component analysis and spectral distribution data including data of the first illumination or data similar to the data of the first illumination, and
• generating the spectral distribution based on the XYZ values of the reference color, the spectral distribution model and the spectral reflectance of the spot in the reference color.

An information processing device comprising:

• a processor to execute a program;
• and
• a memory to store the program which, when executed by the processor, performs processes of,
• acquiring XYZ values being values corresponding to a recognition target region as an image region in an image obtained by photographing an object under first illumination and being values represented in an XYZ color model, a spectral distribution, spectral reflectance in a case of a perfect reflecting diffuser, and determination information indicating a correspondence relationship between Lab values being values in an L*a*b* color space and a color, and calculating Lab values as values corresponding to the recognition target region in the L*a*b* color space by using the XYZ values, the spectral distribution and the spectral reflectance in the case of the perfect reflecting diffuser, and
• determining color of the recognition target region by using the calculated Lab values and the determination information,
• wherein
• when the spectral distribution is generated, acquiring the XYZ values of a reference color and spectral reflectance of a spot in the reference color, the XYZ values of the reference color being calculated based on RGB values acquired from an image region of the reference color in the image obtained by photographing the object under the first illumination, and generating a spectral distribution model by using principal component analysis and spectral distribution data including data of the first illumination or data similar to the data of the first illumination, and
• generating the spectral distribution based on the XYZ values of the reference color, the spectral distribution model and the spectral reflectance of the spot in the reference color.