Method and system for measuring text-rendering quality

• US 8,594,384 B2
• Filed: 11/30/2007
• Issued: 11/26/2013
• Est. Priority Date: 11/30/2007
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Pnueli, Ayelet, Keshet, Renato, Schori, Avi, Ruckenstein, Gitit
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US12/744,912
• Publication Number:
  US 20100303306A1
• Time in Patent Office: 2,188 Days
• Field of Search: None
• US Class Current: 382/112
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern

Abstract

Method embodiments of the present invention provide for semi-automated or fully automated assessment of the quality of device-rendered text, including graphical symbols, characters, and other printable or displayable patterns. Method embodiments of the present invention employ one or more metrics that involve the comparison of input characters, including text characters, symbols, and character-like graphics, with corresponding digital output characters obtained by capturing images of characters rendered by a character-rendering device. The one or more metrics include individual computed relative entropy APQi metrics, reflective of differences in character-to-character distance distributions between one input character c, and the set of input characters c*, a cumulative computed relative entropy APQ, stroke irregularity, contrast measure, sharpness, and background uniformity. These individual metrics can be computed and stored separately as well as output to a user of a character-rendering-quality measurement system, or may be combined together in various ways to produce one or more comprehensive, cumulative metrics for storage and output.

Claims

1. A method that assesses character-rendering quality, the method comprising:

transmitting a test-character set of test characters to a character-rendering device for rendering;

intercepting digital pixel-based character maps for the test characters of the test-character set, used by the character-rendering device for rendering the test characters, to serve as an input-character set of input characters;

capturing, with a computing system, the test characters rendered by the character-rendering device to serve as an output-character set of output characters;

for each input character, generating with the computing system, from the intercepted input characters, one or more first metrics that reflect differences between the input character and at least two of the input characters;

for each output character, generating with the computing system, from the intercepted input characters and the captured output characters, one or more second metrics that reflect differences between the output character and at least two of the input characters; and

outputting one or more indications of character-rendering quality based on the first and second metrics.

2. The method of claim 1 further including:

initially receiving an identity and characteristics of the character-rendering device; and

devising a test-character set appropriate for testing the character-rendering device.

4. The method of claim 1 wherein test characters include:

graphical symbols;

English-language text characters;

punctuation symbols;

foreign-language text characters; and

pixel patterns.

5. The method of claim 1 wherein the one or more first metrics include one or more differences Δ

PQ_i in character-to-character distance distributions between the distance distribution of the distances between a particular input character c_i and all input characters c_k in the input-character set, and wherein the one or more second metrics include one or more differences Δ

PQ_i in character-to-character distance distributions between the distance distribution of the distances between a particular output character ĉ

_i corresponding to input character c_i and all input characters c_k in the input-character set.

6. The method of claim 5 wherein the one or more metrics further includes a cumulative Δ

PQ metric from the generated Δ

PQ_i metrics.

7. The method of claim 5 wherein each Δ

PQ_i is generated according to;

8. The method of claim 7 wherein the cumulative Δ

PQ metric is generated according to;

3. A method that assesses character-rendering quality, the method comprising:

transmitting a test-character set of test characters to a character-rendering device for rendering;

intercepting digital pixel-based character maps for the test characters of the test-character set, used by the character-rendering device for rendering the test characters, to serve as an input-character set of input characters;

capturing, with a computing system, the test characters rendered by the character-rendering device to serve as an output-character set of output characters;

for each input character c_i, generating with the computing system, from the intercepted input characters and the captured output characters, one or more metrics that reflect differences between the input characters and the output characters; and

outputting one or more indications of character-rendering quality based on the one or more metrics, wherein capturing test characters rendered by the character-rendering device to serve as an output-character set of output characters further includes;

capturing images of test characters rendered by the character-rendering device by an image-capturing device;

generating digitally-encoded, pixel-based representations of the test characters rendered by the character-rendering device from the captured images;

tone mapping the digitally-encoded representations of the rendered test characters; and

registering the digitally-encoded representations of the rendered test characters with the input characters in order to generate a set of digitally encoded output characters corresponding to the input characters to serve as the output-character set of output characters.

9. A method that assesses character-rendering quality, the method comprising:

transmitting a test-character set of test characters to a character-rendering device for rendering;

intercepting digital pixel-based character maps for the test characters of the test-character set, used by the character-rendering device for rendering the test characters, to serve as an input-character set of input characters;

capturing, with a computing system, the test characters rendered by the character-rendering device to serve as an output-character set of output characters;

for each input character c_i, generating with the computing system, from the intercepted input characters and the captured output characters, metrics that reflect differences between the input characters and the output characters, including a cumulative metric metric for each set of metrics metric_i which is generated as

10. A method that assesses character-rendering quality, the method comprising:

transmitting a test-character set of test characters to a character-rendering device for rendering;

intercepting digital pixel-based character maps for the test characters of the test-character set, used by the character-rendering device for rendering the test characters, to serve as an input-character set of input characters;

capturing, with a computing system, the test characters rendered by the character-rendering device to serve as an output-character set of output characters;

for each input character c_i, generating with the computing system, from at least one of eroded or dilated transformations of the intercepted input characters superimposed over the captured output characters, one or more outline metrics that reflect differences between the input characters and the output characters; and

outputting one or more indications of character-rendering quality based on the one or more metrics.

11. The method of claim 10 wherein the one or more metrics include further includes a contrast measure metric contrast_measure_i for each input character c_i and corresponding output character ĉ

_i as;

12. The method of claim 10 wherein the one or more metrics include further includes a sharpness metric sharpness_i for each input character c_i and corresponding output character ĉ

_i as;

13. The method of claim 10 wherein the one or more metrics include further includes a background uniformity metric background_uniformity_i for each input character c_i and corresponding output character ĉ

_i as;

background_uniformity_i=std({circumflex over (c)} in (ĉ

_i−

{tilde over (c)}_i))

wherein background uniformity is a standard deviation of the pixel values of the output character ĉ

outside of the dilated-input-character ĉ

_i boundary superimposed over the output character.

14. The method of claim 10 wherein the one or more metrics include further includes a stroke irregularity metric stroke_irregularity_i for each input character c_i and corresponding output character ĉ

_i as;