HP INCFollow


In the development of system that can analyze image quality of a printed page, there is variability in

what the customer will consider unacceptable image quality for their print job. The algorithms, be them

expert rule based, deep learning, or some other AI variant, will output a value for the image quality that

fits within a range. The low end of that range is generally considered good image quality, while the high

end is considered poor image quality. With customer variance, any system employing the analysis of

image quality will have to take that variance in account. One way to account for this is to allow percustomer,

per‐device customization of the acceptable image quality threshold.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.