Methods and Systems for Identifying Text Orientation in a Digital Image

• US 20080317341A1
• Filed: 06/21/2007
• Published: 12/25/2008
• Est. Priority Date: 06/21/2007
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Speigle, Jon M., Ferman, Ahmet Mufit
• Granted Patent: US 8,144,989 B2
• Time in Patent Office: Days
• US Class Current: 382/170
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees

Abstract

Aspects of the present invention relate to systems and methods for determining text orientation in a digital image.

Claims

1. A method for determining a text orientation in a digital image, said method comprising:

a) computing, for each of a plurality of text-object pairs in a digital image, a first alignment feature value for a first alignment feature, thereby producing a first plurality of feature values;

b) computing, for each of said plurality of text-object pairs, a second alignment feature value for a second alignment feature, thereby producing a second plurality of feature values;

c) generating a first histogram of said first plurality of feature values;

d) generating a second histogram of said second plurality of feature values; and

e) determining a text orientation in a digital image based on said first histogram and said second histogram.

2. A method according to claim 1, wherein said determining is related to character alignment.

3. A method according to claim 1, wherein said determining is related to a relative frequency of occurrence of text characters with ascenders and text characters with descenders in a written language.

4. A method according to claim 1, wherein at least one pair of said plurality of text-object pairs comprises a first text object and a second text object, wherein said first text object and said second text object are adjacent text objects in said digital image.

5. A method according to claim 1, wherein at least one pair of said plurality of text-object pairs comprises a first text object and a second text object, wherein said first text object and said second text object are not adjacent text objects in said digital image.

6. A method according to claim 1, wherein each of said plurality of text-object pairs comprises a first text object and a second text object, wherein said first text object is not substantially the same size as said second text object.

7. A method according to claim 1 further comprising projecting each of said plurality of text-object pairs according to a skew angle prior to said computing said first alignment feature value for said first alignment feature and prior to said computing said second alignment feature value for said second alignment feature.

8. A method according to claim 1, wherein each of said plurality of text-object pairs comprises a first text object and a second text object;

and;

a) said computing, for each of said plurality of text-object pairs, said first alignment feature value for said first alignment feature comprises;

i) determining a first absolute difference between a first bounding edge of said first text object and an associated first bounding edge of said second text object, thereby associating said first histogram with said first bounding edge; and

b) said computing, for each of said plurality of text-object pairs, said second alignment feature value for said second alignment feature comprises;

i) determining a second absolute difference between a second bounding edge of said first text object and an associated second bounding edge of said second text object, thereby associating said second histogram with said second bounding edge.

9. A method according to claim 8, wherein said determining said text orientation comprises:

a) determining a first frequency-of-occurrence from said first histogram, wherein said first frequency-of-occurrence corresponds to a substantially zero first absolute difference;

b) determining a second frequency-of-occurrence from said second histogram, wherein said second frequency-of-occurrence corresponds to a substantially zero second absolute difference;

c) associating a baseline-side of said text orientation with said first bounding edge when said first frequency-of-occurrence is greater than said second frequency-of-occurrence and text characters with ascenders occur more frequently than text characters with descenders in a written language; and

d) associating said baseline-side of said text orientation with said second bounding edge when said first frequency-of-occurrence is less than said second frequency-of-occurrence and text characters with ascenders occur more frequently than text characters with descenders in said written language.

10. A method according to claim 8, wherein said determining said text orientation comprises:

a) determining a first frequency-of-occurrence from said first histogram, wherein said first frequency-of-occurrence corresponds to a substantially zero first absolute difference;

b) determining a second frequency-of-occurrence from said second histogram, wherein said second frequency-of-occurrence corresponds to a substantially zero second absolute difference;

c) associating said baseline-side of said text orientation with said first bounding edge when said first frequency-of-occurrence is less than said second frequency-of-occurrence and text characters with descenders occur more frequently than text characters with ascenders in a written language; and

d) associating said baseline-side of said text orientation with said second bounding edge when said first frequency-of-occurrence is greater than said second frequency-of-occurrence and text characters with descenders occur more frequently than text characters with ascenders in said written language.

11. A method according to claim 1 further comprising:

a) computing, for each of said plurality of text-object pairs, a third alignment feature value for a third alignment feature, thereby producing a third plurality of feature values;

b) computing, for each of said plurality of text-object pairs, a fourth alignment feature value for a fourth alignment feature, thereby producing a fourth plurality of feature values

c) generating a third histogram of said third plurality of feature values;

d) generating a fourth histogram of said fourth plurality of feature values; and

e) wherein said determining said text orientation in said digital image based on said first histogram, said second histogram, said third histogram, said fourth histogram.

12. A method according to claim 11, wherein each of said plurality of text-object pairs comprises a first text object and a second text object;

and;

a) said computing, for each of said plurality of text-object pairs, said third alignment feature value for said third alignment feature comprises;

i) determining a third absolute difference between a third bounding edge of said first text object and an associated third bounding edge of said second text object, thereby associating said third histogram with said third bounding edge; and

b) said computing, for each of said plurality of text-character pairs, said fourth alignment feature value for said fourth alignment feature comprises;

i) determining a fourth absolute difference between a fourth bounding edge of said first text object and an associated fourth bounding edge of said second text object, thereby associating said fourth histogram with said fourth bounding edge.

13. A method according to claim 12, wherein said determining said text orientation comprises:

a) determining a first frequency-of-occurrence from said first histogram, wherein said first frequency-of-occurrence corresponds to a substantially zero first absolute difference;

b) determining a second frequency-of-occurrence from said second histogram, wherein said second frequency-of-occurrence corresponds to a substantially zero second absolute difference;

c) determining a third frequency-of-occurrence from said third histogram, wherein said third frequency-of-occurrence corresponds to a substantially zero third absolute difference;

d) determining a fourth frequency-of-occurrence from said fourth histogram, wherein said fourth frequency-of-occurrence corresponds to a substantially zero fourth absolute difference;

e) determining a maximum frequency-of-occurrence of said first frequency-of-occurrence, said second frequency-of-occurrence, said third frequency-of-occurrence and said fourth frequency-of-occurrence, thereby determining a histogram associated with said maximum frequency-of-occurrence; and

f) associating a baseline-side of said text orientation with said bounding edge associated with said histogram associated with said maximum frequency-of-occurrence when text characters with ascenders occur more frequently than text characters with descenders in a written language.

14. A method according to claim 12, wherein said determining said text orientation comprises:

a) determining a first frequency-of-occurrence from said first histogram, wherein said first frequency-of-occurrence corresponds to a substantially zero first absolute difference;

b) determining a second frequency-of-occurrence from said second histogram, wherein said second frequency-of-occurrence corresponds to a substantially zero second absolute difference;

c) determining a third frequency-of-occurrence from said third histogram, wherein said third frequency-of-occurrence corresponds to a substantially zero third absolute difference;

d) determining a fourth frequency-of-occurrence from said fourth histogram, wherein said fourth frequency-of-occurrence corresponds to a substantially zero fourth absolute difference;

e) determining a maximum frequency-of-occurrence of said first frequency-of-occurrence, said second frequency-of-occurrence, said third frequency-of-occurrence and said fourth frequency-of-occurrence, thereby determining a histogram associated with said maximum frequency-of-occurrence; and

f) associating a baseline-side of said text orientation with a bounding edge opposite of said bounding edge associated with said histogram associated with said maximum frequency-of-occurrence when text characters with descenders occur more frequently than text characters with ascenders in a written language.

15. A method according to claim 1 further comprising correcting said digital image for a skew angle.

16. A system for determining a text orientation in a digital image, said system comprising:

a) a first alignment-feature-value calculator for computing, for each of a plurality of text-object pairs in a digital image, a first alignment feature value for a first alignment feature, thereby producing a first plurality of feature values;

b) a second alignment-feature-value calculator for computing, for each of said plurality of text-object pairs, a second alignment feature value for a second alignment feature, thereby producing a second plurality of feature values

c) a first histogram generator for generating a first histogram of said first plurality of feature values;

d) a second histogram generator for generating a second histogram of said second plurality of feature values; and

e) an orientation determiner for determining a text orientation in a digital image based on said first histogram and said second histogram.

17. A system according to claim 16 further comprising a skew projector for projecting each of said plurality of text-object pairs according to a skew angle prior to said computing said first alignment feature value for said first alignment feature and prior to said computing said second alignment feature value for said second alignment feature.

18. A system according to claim 16, wherein each of said plurality of text-object pairs comprises a first text object and a second text object;

and;

a) said first alignment-feature-value calculator comprises;

i) a first subtractor for determining a first absolute difference between a first bounding edge of said first text object and an associated first bounding edge of said second text object, thereby associating said first histogram with said first bounding edge; and

b) said second alignment-feature-value calculator comprises;

i) a second subtractor for determining a second absolute difference between a second bounding edge of said first text object and an associated second bounding edge of said second text object, thereby associating said second histogram with said second bounding edge.

19. A system according to claim 18, wherein said orientation determiner comprises:

a) a first frequency-of-occurrence determiner for determining a first frequency-of-occurrence from said first histogram, wherein said first frequency-of-occurrence corresponds to a substantially zero first absolute difference;

b) a second frequency-of-occurrence determiner for determining a second frequency-of-occurrence from said second histogram, wherein said second frequency-of-occurrence corresponds to a substantially zero second absolute difference; and

c) a baseline associator for;

i) associating a baseline-side of said text orientation with said first bounding edge when said first frequency-of-occurrence is greater than said second frequency-of-occurrence and text characters with ascenders occur more frequently than text characters with descenders in a written language; and

ii) associating said baseline-side of said text orientation with said second bounding edge when said first frequency-of-occurrence is less than said second frequency-of-occurrence and text characters with ascenders occur more frequently than text characters with descenders in said written language.

20. A system according to claim 18, wherein said orientation determiner comprises:

a) a first frequency-of-occurrence determiner for determining a first frequency-of-occurrence from said first histogram, wherein said first frequency-of-occurrence corresponds to a substantially zero first absolute difference;

b) a second frequency-of-occurrence determiner for determining a second frequency-of-occurrence from said second histogram, wherein said second frequency-of-occurrence corresponds to a substantially zero second absolute difference; and

c) a baseline associator for;

i) associating said baseline-side of said text orientation with said first bounding edge when said first frequency-of-occurrence is less than said second frequency-of-occurrence and text characters with descenders occur more frequently than text characters with ascenders in a written language; and

ii) associating said baseline-side of said text orientation with said second bounding edge when said first frequency-of-occurrence is greater than said second frequency-of-occurrence and text characters with descenders occur more frequently than text characters with ascenders in said written language.

21. A method for determining a text orientation in a digital image, said method comprising:

a) selecting a first text object from a digital image;

b) determining, for said first text object, a first bounding box;

c) selecting a second text object from said digital image;

d) determining, for said second text object, a second bounding box;

e) when the size of said first text object is substantially different than the size of said second text object,

i) determining, for said first text object and said second text object, a first bounding-box feature value for a first bounding-box feature, wherein said first bounding-box feature is related to a first edge of said first bounding box;

ii) updating a first histogram based on said first bounding-box feature value;

iii) determining, for said first text object and said second text object, a second bounding-box feature value for a second bounding-box feature, wherein said second bounding-box feature is related to a second edge of said first bounding box;

iv) updating a second histogram based on said second bounding-box feature value;

v) determining, for said first text object and said second text object, a third bounding-box feature value for a third bounding-box feature, wherein said third bounding-box feature is related to a third edge of said first bounding box;

vi) updating a third histogram based on said third bounding-box feature value;

vii) determining, for said first text object and said second text object, a fourth bounding-box feature value for a fourth bounding-box feature, wherein said fourth bounding-box feature is related to a fourth edge of said first bounding box;

viii) updating a fourth histogram based on said fourth bounding-box feature value;

f) determining a text orientation in said digital image based on said first histogram, said second histogram, said third histogram and said fourth histogram.

22. A method according to claim 21, wherein said first text object and said second text object are adjacent text objects in said digital image.

23. A method according to claim 21, wherein said first text object and said second text object are not adjacent text objects in said digital image.