Analyzing font similarity for presentation

• US 9,317,777 B2
• Filed: 10/04/2013
• Issued: 04/19/2016
• Est. Priority Date: 10/04/2013
• Status: Active Grant

• Current Assignee: Monotype Imaging (Monotype Imaging Holdings, Inc.)
• Original Assignee: Monotype Imaging (Monotype Imaging Holdings, Inc.)
• Inventors: Kaasila, Sampo Juhani, Vijay, Anand, Bansal, Jitendra Kumar
• Primary Examiner(s): Wu, Xiao
• Assistant Examiner(s): Akhavannik, Mohammad H
• Application Number:
  US14/046,609
• Publication Number:
  US 20150097842A1
• Time in Patent Office: 928 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 40/109 Font handling; Temporal or kinetic typography
• CPC Class Codes: G06F 40/194 Calculation of difference between files
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 30/245 Font recognition

Abstract

A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor to execute the instructions to perform operations that include receiving data representing features of a first font and data representing features of a second font. The first font and the second font are capable of representing one or more glyphs. Operations also include receiving survey-based data representing the similarity between the first and second fonts, and, training a machine learning system using the features of the first font, the features of the second font and the survey-based data that represents the similarity between the first and second fonts.

Claims

1. A computing device implemented method comprising:

receiving data representing features of a first font and data representing features of a second font, wherein the first font and the second font are capable of representing one or more glyphs;

receiving data representing the similarity between the first and second fonts determined by one or more individuals;

training a machine learning system by calculating a cost function from a difference between the features of the first font and the features of the second font, and from the data that represents the similarity between the first and second fonts determined by one or more individuals;

using the machine learning system to determine a level of similarity for a pair of fonts, wherein the pair of fonts includes at least one of the first font and the second font; and

producing a list of fonts for presentation based on the level of similarity for the font pair, wherein the presented order of fonts in the produced list is based upon a level of similarity between a focus font and other fonts.

2. The computing device implemented method of claim 1, wherein training the machine learning system includes calculating a level of similarity between the first font and the second font from the first font features and the second font features.

3. The computing device implemented method of claim 2, wherein calculating the level of similarity includes determining the difference between features of the first font and corresponding features of the second font.

4. The computing device implemented method of claim 2, wherein training the machine learning system includes comparing the calculated level of similarity between the first and second fonts and a value that represents the similarity between the first and second fonts from the data determined by one or more individuals.

5. The computing device implemented method of claim 1, wherein training the machine learning system includes minimizing the cost function.

6. The computing device implemented method of claim 1, wherein the machine learning system implements a neural network.

7. The computing device implemented method of claim 1, wherein the produced list includes a selected focus font.

8. The computing device implemented method of claim 1, wherein the presented order of the fonts in the produced list is based upon a level of similarity between a focus font and other fonts, and, a level of similarity between fonts other than a focus font.

9. The computing device implemented method of claim 1, wherein a standard deviation of the amount of grey present in a glyph is used to calculate at least one of the features of the first font.

10. The computing device implemented method of claim 1, wherein the features of a first font are produced from one or more bitmap images rendered by the machine learning system.

11. A system comprising:

a computing device comprising;

a memory configured to store instructions; and

a processor to execute the instructions to perform operations comprising;

receiving data representing features of a first font and data representing features of a second font, wherein the first font and the second font are capable of representing one or more glyphs;

receiving data representing the similarity between the first and second fonts determined by one or more individuals;

training a machine learning system by calculating a cost function from a difference between the features of the first font and the features of the second font, and from the data that represents the similarity between the first and second fonts determined by one or more individuals;

using the machine learning system to determine a level of similarity for a pair of fonts, wherein the pair of fonts includes at least one of the first font and the second font; and

producing a list of fonts for presentation based on the level of similarity for the font pair, wherein the presented order of fonts in the produced list is based upon a level of similarity between a focus font and other fonts.

12. The system of claim 11, wherein training the machine learning system includes calculating a level of similarity between the first font and the second font from the first font features and the second font features.

13. The system of claim 12, wherein calculating the level of similarity includes determining the difference between features of the first font and corresponding features of the second font.

14. The system of claim 12, wherein training the machine learning system includes comparing the calculated level of similarity between the first and second fonts and a value that represents the similarity between the first and second fonts from the data determined by one or more individuals.

15. The system of claim 11, wherein training the machine learning system includes minimizing the cost function.

16. The system of claim 11, wherein the machine learning system implements a neural network.

17. The system of claim 11, wherein the produced list includes a selected focus font.

18. The system of claim 11, wherein the presented order of the fonts in the produced list is based upon a level of similarity between a focus font and other fonts, and, a level of similarity between fonts other than a focus font.

19. The system of claim 11, wherein a standard deviation of the amount of grey present in a glyph is used to calculate at least one of the features of the first font.

20. The system of claim 11, wherein the features of a first font are produced from one or more bitmap images rendered by the machine learning system.

21. One or more non-transitory computer readable media storing instructions that are executable by a processing device, and upon such execution cause the processing device to perform operations comprising:

receiving data representing features of a first font and data representing features of a second font, wherein the first font and the second font are capable of representing one or more glyphs;

receiving data representing the similarity between the first and second fonts determined by one or more individuals;

training a machine learning system by calculating a cost function from a difference between the features of the first font and the features of the second font, and from the data that represents the similarity between the first and second fonts determined by one or more individuals;

using the machine learning system to determine a level of similarity for a pair of fonts, wherein the pair of fonts includes at least one of the first font and the second font; and

producing a list of fonts for presentation based on the level of similarity for the font pair, wherein the presented order of fonts in the produced list is based upon a level of similarity between a focus font and other fonts.

22. The non-transitory computer readable media of claim 21, wherein training the machine learning system includes calculating a level of similarity between the first font and the second font from the first font features and the second font features.

23. The non-transitory computer readable media of claim 22, wherein calculating the level of similarity includes determining the difference between features of the first font and corresponding features of the second font.

24. The non-transitory computer readable media of claim 22, wherein training the machine learning system includes comparing the calculated level of similarity between the first and second fonts and a value that represents the similarity between the first and second fonts from the data determined by one or more individuals.

25. The non-transitory computer readable media of claim 21, wherein training the machine learning system includes minimizing the cost function.

26. The non-transitory computer readable media of claim 21, wherein the machine learning system implements a neural network.

27. The non-transitory computer readable media of claim 21, wherein the produced list includes a selected focus font.

28. The non-transitory computer readable media of claim 21, wherein the presented order of the fonts in the produced list is based upon a level of similarity between a focus font and other fonts, and, a level of similarity between fonts other than a focus font.

29. The non-transitory computer readable media of claim 21, wherein a standard deviation of the amount of grey present in a glyph is used to calculate at least one of the features of the first font.

30. The non-transitory computer readable media of claim 21, wherein the features of a first font are produced from one or more bitmap images rendered by the machine learning system.