Method and system for looking up words on a display screen by OCR comprising a set of base forms of recognized inflected words

• US 9,031,831 B1
• Filed: 01/14/2011
• Issued: 05/12/2015
• Est. Priority Date: 01/14/2010
• Status: Expired due to Fees

• Current Assignee: ABBYY Production LLC (ABBYY Software)
• Original Assignee: ABBYY Development LLC
• Inventors: Levchenko, Dmitry
• Primary Examiner(s): KAZEMINEZHAD, FARZAD
• Application Number:
  US13/006,813
• Time in Patent Office: 1,579 Days
• Field of Search: 704/2, 704/246, 704/3
• US Class Current: 704/9
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Embodiments of the present invention disclose a dictionary lookup method and an electronic device that implements the dictionary lookup method. The dictionary lookup method allows a user to quickly obtain meanings and translations of words from electronic dictionaries while reading a text on a display screen of the electronic device, wherein reading text is utilized by performing an optical character recognition comprising of determining a set of base forms of each inflected recognized word. Advantageously, in one embodiment the meanings (e.g., the base forms) and translations may be displayed in a balloon, in a pop-up window, as subscript, as superscript, or in any other suitable manner when the user touches a word on the display screen, in one embodiment.

Claims

1. A computer implemented method comprising:

displaying text image content on a display screen;

detecting user input associated with a portion of the display screen;

establishing coordinates associated with the user input;

identifying a rectangular region of the text image content indicated by the coordinates, wherein the rectangular region contains text;

performing character recognition on the identified rectangular region to extract text from the text image content resulting in a recognition result;

comparing the recognition result with similar word forms in a first morphology dictionary to correct errors in the recognition result;

identifying the extracted text associated with the rectangular region of the text image content;

determining a set of base forms of any inflected form of the word in the extracted text using a second morphological dictionary;

performing a dictionary lookup based on the identified extracted text comprising;

determining a set of base forms of any inflected form of a word in the extracted text using a second morphological dictionary;

identifying a set of translations of the set of base forms from a first dictionary;

determining a result translation of the word from the retrieved set of translations, wherein the result translation is a most likely part of speech;

and displaying the result translation of the dictionary lookup on the display screen.

2. The method of claim 1, wherein the user input comprises one of pointer-based or haptic-based input.

3. The method of claim 2, wherein the haptic-based input comprises touch-based inputs.

4. The method of claim 2, wherein the pointer-based input comprises pen-based inputs.

5. The method of claim 1, wherein performing the dictionary lookup further comprises:

generating a word query comprising at least one word based on the recognition result; and

passing the word query to at least first dictionary.

6. The method of claim 5, wherein the generating the word query comprises:

performing morphological analysis to identify a base form of each word in the word query.

7. The method of claim 1, wherein identifying the text comprises selecting at least one word from a text area of the content indicated by the coordinates.

8. The method of claim 1, wherein identifying the rectangular region includes identifying a smallest rectangular region of the text image content indicated by the coordinates and which contains at least a portion of a word.

9. The method of claim 1, wherein performing the text recognition operation comprises applying an optical character recognition technique to the identified rectangular region to form a recognition result comprising at least one word.

10. The method of claim 1, wherein the displaying comprises displaying at least a most likely result of the dictionary lookup.

11. The method of claim 1, wherein the displaying comprises displaying the result of the dictionary lookup in the form of one of a pop-up window, superscript text, subscript text, and a text balloon.

12. The method of claim 1, wherein performing the dictionary lookup comprises accessing at least one dictionary selected from the group consisting of a local dictionary and a remote dictionary.

13. The method of claim 1, further comprising playing back an audio pronunciation associated with the result of the dictionary lookup.

14. An electronic device comprising:

a processor; and

a memory coupled to the processor, the memory storing instructions which when executed by the processor cause the processor to perform operations comprising;

displaying text image content on a display screen;

detecting user input associated with a portion of the display screen;

establishing coordinates associated with the user input;

identifying a rectangular region of the text image content indicated by the coordinates, wherein the rectangular region contains text;

performing character recognition on the identified rectangular region to extract text from the text image content resulting in a recognition result;

comparing the recognition result with similar word forms in a first morphology dictionary to correct errors in the recognition result;

identifying the extracted text associated with the rectangular region of the text image content;

determining a set of base forms of any inflected form of the word in the extracted text using a second morphological dictionary;

performing a dictionary lookup based on the identified extracted text comprising;

determining a set of base forms of any inflected form of a word in the extracted text using a second morphological dictionary;

identifying a set of translations of the set of base forms from a first dictionary;

determining a result translation of the word from the retrieved set of translations, wherein the result translation is a most likely part of speech; and

displaying the result translation of the dictionary lookup on the display screen.

15. The electronic device of claim 14, wherein the user input comprises one of pointer-based or haptic-based input.

16. The electronic device of claim 15, wherein the haptic-based input comprises touch-based inputs.

17. The electronic device of claim 15, wherein the pointer-based input comprises pen-based inputs.

18. The electronic device of claim 14, wherein performing the dictionary lookup further comprises generating a word query comprising at least one word based on the recognition result and passing the word query to at least the first dictionary.

19. The electronic device of claim 18, wherein the generating the word query comprises performing morphological analysis to identify a base form of each word in the word query.

20. The electronic device of claim 14, wherein identifying the text includes selecting at least one word from a text area of the text image content indicated by the coordinates.

21. The electronic device of claim 14, wherein identifying the rectangular region comprise identifying a smallest rectangular region of the text image content indicated by the coordinates and which contains at least a portion of a word.

22. The electronic device of claim 14, wherein the displaying comprises displaying at least a most likely result of the dictionary lookup.

23. The electronic device of claim 14, wherein the displaying comprises displaying the result of the dictionary lookup in the form of one of a pop-up window, superscript text, subscript text, and a text balloon.

24. The electronic device of claim 14, wherein performing the dictionary lookup comprises accessing at least one dictionary selected from the group consisting of a local dictionary and a remote dictionary.

25. The electronic device of claim 14, wherein the method further comprises playing back an audio pronunciation associated with the result of the dictionary lookup.

26. A non-transitory computer-readable medium having stored thereon a sequence of instruction which when executed by a system cause the system to perform a method, comprising:

displaying text image content on a display screen;

detecting user input associated with a portion of the display screen;

establishing coordinates associated with the user input;

identifying a rectangular region of the text image content indicated by the coordinates, wherein the rectangular region contains text;

performing character recognition on the identified rectangular region to extract text from the text image content resulting in a recognition result;

comparing the recognition result with similar word forms in a first morphology dictionary to correct errors in the recognition result;

identifying the extracted text associated with the rectangular region of the text image content;

determining a set of base forms of any inflected form of the word in the extracted text using a second morphological dictionary;

performing a dictionary lookup based on the identified extracted text comprising;

determining a set of base forms of any inflected form of a word in the extracted text using a second morphological dictionary;

identifying a set of translations of the set of base forms from a first dictionary;

determining a result translation of the word from the retrieved set of translations, wherein the result translation is a most likely part of speech; and

displaying the result translation of the dictionary lookup on the display screen.

27. The non-transitory computer-readable medium of claim 26, wherein identifying the extracted text associated with the rectangular region of the text image content includes selecting at least one word from a text area of the content indicated by the coordinates.