Assessing printer quality by assigning quality scores to images
Disclosed here is a system enabling users/customers to receive an objective assessment of the performance of a printer. This is accomplished by comparing a quality score of an earlier-in-time image with a quality score of a later-in-time image. A processor analyzes each image based on several criteria and uses various image-analysis methods, to flag errors within an image. A numeric quality score, based on the number of errors, is provided to the user to objectively evaluate whether the printer has degraded or not. Thus, the user can objectively present an argument to a salesperson or manufacturer that the user is due a remedy.
1. A method for scoring the quality of a printer, the method comprising:
capturing a first image of a first printout;
storing the first image as a reference image;
capturing a second image of a second printout that is printed at a later time than the first printout;
evaluating one or more properties of the first and second images; and
providing (i) a first numeric quality score for the first image and (ii) and a second numeric quality score for the second image.
2. The method of claim 1 , further comprising:
communicating to a processor the first and second numeric quality scores; and
distributing, via the processor, the reference image to another network-connected printer.
3. The method of claim 1 , wherein the one or more properties include sharpness, noise, dynamic range, tone reproduction, contrast, color accuracy, distortion, vignetting, exposure accuracy, lateral chromatic aberration, lens flare, color moiré, size, frequency, number of mismatched areas, or any combination thereof.
4. The method of claim 1 , wherein each property is given a numeric value for each of the first and second images based on quality.
5. The method of claim 4 , wherein for each of the first and second images, the numeric quality score is the sum of the numeric values determined for the one or more properties.
6. The method of claim 1 , wherein the first and second printouts are of a same image.
7. The method of claim 1 , wherein the first and second printouts are printed by different printers.
8. A method performed by a processor, the method comprising:
acquiring
(i) a first image of a first printout that is produced by a printer, and
(ii) a second image of a second printout that is produced by the printer subsequent to the first printout;
evaluating a property of the first and second images;
providing, for the first image, a first numeric quality score based on the evaluated property of the first image; and
providing, for the second image, a second numeric quality score based on the evaluated property of the second image.
9. The method of claim 8 , wherein the processor is part of the printer.
10. The method of claim 8 , wherein the processor is external to the printer.
11. The method of claim 8 ,
wherein the property is one of multiple properties evaluated across the first and second images,
wherein the first numeric quality score is representative of an average of the evaluated properties of the first image, and
wherein the second numeric quality score is representative of an average of the evaluated properties of the second image.
12. The method of claim 11 , wherein each evaluated property of the first and second images is evaluated on a predetermined scale having an upper bound and a lower bound.
13. The method of claim 12 , wherein the upper bound is 100 and the lower bound is 0.
14. The method of claim 8 , wherein said evaluating comprises employing an anomaly-detection technique to surface anomalies, if any, in the first and second images.
15. The method of claim 14 ,
wherein the first numeric quality score is based on a number of anomalies detected in the first image, and
wherein the second numeric quality score is based on a number of anomalies detected in the second image.
16. A method for quantitatively assessing quality of a printer, the method comprising:
acquiring
(i) a first image of a first printout that is produced by a printer, and
(ii) a second image of a second printout that is produced by the printer subsequent to the first printout;
producing a first numeric score by evaluating a property of the first image;
producing a second numeric score by evaluating the property of the second image; and
comparing the second numeric score to the first numeric score to establish whether the printer has an issue that needs to be resolved.
17. The method of claim 16 ,
wherein the first numeric score is based on a number of anomalies detected in the first image, and
wherein the second numeric score is based on a number of anomalies detected in the second image.
18. The method of claim 17 , wherein the anomalies are detected in the first and second images using a k-nearest neighbors algorithm, a local outlier factor algorithm, an isolation forest, a Bayesian network, a hidden Markov model, a cluster analysis algorithm, or an ensemble technique.
19. The method of claim 17 , wherein the anomalies are detected in the first and second images using a cluster analysis algorithm that clusters pixels together based on commonalities, identifies pixels that do not have commonalities with any clusters exceeding a given size, and then labels the identified pixels as representative of an anomaly.