Lower modifier detection and extraction from devanagari text images to improve OCR performance

• US 9,064,191 B2
• Filed: 03/08/2013
• Issued: 06/23/2015
• Est. Priority Date: 01/26/2012
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Krishna Kumar, Raj Kumar, Baheti, Pawan Kumar
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US13/791,188
• Publication Number:
  US 20130195360A1
• Time in Patent Office: 837 Days
• Field of Search: 382/173, 382/177, 382/178, 382/185, 382/186, 382/203
• US Class Current: 1/1
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/146 Aligning or centring of the image pick-up or image-field
• CPC Class Codes: G06V 30/293 of characters other than Kanji, Hiragana or Katakana

Abstract

Systems, apparatus and methods for extracting lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test are presented. The method obtains the word image and performing a plurality of tests (e.g., a first test, a second test and a third test). The first test determines whether a vertical line spanning the height of the word image exists. The second test determines whether a jump of a number of components in the lower portion of the word image exists. The third test determines sparseness in a lower portion of the word image. The plurality of tests may run sequentially and/or in parallel. Results from the plurality of tests are used to decide whether a lower modifier exists by comparing and accumulating test results from the plurality of tests.

Claims

1. A method to extract lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test, the method comprising:

obtaining the word image, wherein the word image defines a height of the word image and a width of the word image;

performing the first test to determine whether a vertical line spanning the height of the word image is present;

performing the second test to determine whether a jump of a number of components exist in a lower portion of the word image;

performing the third test to determine sparseness in the lower portion of the word image; and

comparing test results from the first test, the second test and the third test to decide whether a lower modifier exists.

2. The method of claim 1, wherein obtaining the word image comprises:

obtaining an image containing at least one region having text;

isolating the at least one region containing text; and

extracting the word image from the at least one region.

3. The method of claim 1, wherein obtaining the word image comprises converting the word image into a binary representation.

4. The method of claim 1, wherein the word image comprises a headline, wherein the word image further defines a height of the word image below the headline, and wherein the first test comprises:

determining a presence of the vertical line;

determining a height of the vertical line;

comparing the height of the vertical line to the height of the word image below the headline plus a threshold length; and

incrementing a first variable by a first threshold to indicate a probable lack of a lower modifier, if the height of the word image below the headline is less than the height of the vertical line plus the threshold length, and otherwise, incrementing a second variable by a second threshold.

5. The method of claim 1, wherein the jump exists when a count increase by at least a jump threshold, and wherein the second test comprises:

scanning a bottom portion of the word image to determine whether the jump in the number of components exists; and

incrementing a first variable by a third threshold when no jump exists thereby indicating a probable lack of the lower modifier, and otherwise, incrementing a second variable by a fourth threshold.

6. The method of claim 5, wherein the jump threshold is three.

7. The method of claim 1, wherein the third test comprises:

performing a vertical projection of the lower portion of the word image;

counting components having at least a height greater than a height threshold or a width greater than a width threshold to result in a component count; and

incrementing a first variable by a fifth threshold to indicate a probable lack of the lower modifier, if the component count is greater than a threshold, and otherwise, incrementing a second variable by a sixth threshold.

8. The method of claim 1, wherein the word image comprises Devanagari text.

9. The method of claim 1, further comprising extracting a lower modifier based on the comparing.

10. The method of claim 1, further comprising determining a location of a lower modifier based on results from at least one of the plurality of tests.

11. A mobile device for extracting lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test, the mobile device comprising:

a camera;

a display; and

a processor coupled to the camera and the display, wherein the processor comprises instructions to;

obtain the word image, wherein the word image defines a height of the word image and a width of the word image;

perform the first test to determine whether a vertical line spanning the height of the word image is present;

perform the second test to determine whether a jump of a number of components exist in a lower portion of the word image;

perform the third test to determine sparseness in the lower portion of the word image; and

compare test results from the first test, the second test and the third test to decide whether a lower modifier exists.

12. The mobile device of claim 11, further comprising instructions to:

obtain an image containing at least one region having text;

isolate the at least one region containing text; and

extract the word image from the at least one region.

13. The mobile device of claim 11, further comprising instructions to extract a lower modifier based on the comparing.

14. The mobile device of claim 11, further comprising instructions to determine a location of a lower modifier based on results from at least one of the plurality of tests.

15. A mobile device for extracting lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test, the mobile device comprising:

means for obtaining the word image, wherein the word image defines a height of the word image and a width of the word image;

means for performing the first test to determine whether a vertical line spanning the height of the word image is present;

means for performing the second test to determine whether a jump of a number of components exist in a lower portion of the word image;

means for performing the third test to determine sparseness in the lower portion of the word image; and

means for comparing test results from the first test, the second test and the third test to decide whether a lower modifier exists.

16. The mobile device of claim 15, further comprising:

means for obtaining an image containing at least one region having text;

means for isolating the at least one region containing text; and

means for extracting the word image from the at least one region.

17. The mobile device of claim 15, further comprising means for extracting a lower modifier based on the comparing.

18. The mobile device of claim 15, further comprising means for determining a location of a lower modifier based on results from at least one of the plurality of tests.

19. A mobile device for extracting lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test, the mobile device comprising a processor and a memory wherein the memory includes software instructions to:

obtain the word image, wherein the word image defines a height of the word image and a width of the word image;

perform the first test to determine whether a vertical line spanning the height of the word image is present;

perform the second test to determine whether a jump of a number of components exist in a lower portion of the word image;

perform the third test to determine sparseness in the lower portion of the word image; and

compare test results from the first test, the second test and the third test to decide whether a lower modifier exists.

20. The mobile device of claim 19, wherein the instructions further comprise instructions to extract a lower modifier based on the comparing.

21. The mobile device of claim 19, wherein the instructions further comprise instructions to determine a location of a lower modifier based on results from at least one of the plurality of tests.

22. A non-volatile computer-readable storage medium including program code stored thereon, comprising program code to extract lower modifiers from a word image, before performing optical character recognition (OCR), based on a plurality of tests comprising a first test, a second test and a third test, the program code to:

obtain the word image, wherein the word image defines a height of the word image and a width of the word image;

perform the first test to determine whether a vertical line spanning the height of the word image is present;

perform the second test to determine whether a jump of a number of components exist in a lower portion of the word image;

perform the third test to determine sparseness in the lower portion of the word image; and

compare test results from the first test, the second test and the third test to decide whether a lower modifier exists.