System and method for improved optical character recognition for automated set-top box testing

• US 9,516,304 B2
• Filed: 12/22/2011
• Issued: 12/06/2016
• Est. Priority Date: 11/26/2010
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: Friel, Liam
• Primary Examiner(s): Alam, Mushfikh
• Application Number:
  US13/989,777
• Publication Number:
  US 20130347050A1
• Time in Patent Office: 1,811 Days
• Field of Search: 725/107
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: H04N 17/00 Diagnosis, testing or measuring for television systems or their details
• CPC Class Codes: H04N 17/04 for receivers
• CPC Class Codes: H04N 17/045 Self-contained testing apparatus

Abstract

The present application provides a user configurable test system for set-top boxes (STB) and other consumer devices providing video output. In particular, it provides for a method of improving an Optical Character Recognition (OCR) process in such test systems.

Claims

1. A test system comprising:

a processor to;

obtain a video frame, comprising images in sequence, from a device under test;

select a filter configuration for at least one filter to test;

filter an image included in the images in sequence using the filter configuration to generate a filtered image;

extract text from the filtered image using an optical character recognition (OCR) engine;

determine a filter performance for the image based on comparing the text extracted from the filtered image to an expected result;

when the filter performance is a positive result, filter another image included in the images in sequence using the filter configuration;

when the filter performance is a negative result, repeatedly select a different filter configuration and filter the image using the different filter configuration until the positive result is determined; and

determine a suitable filter configuration when the filter performance for each image in the images in sequence is positive for a same filter configuration.

2. A test system according to claim 1, where the at least one filter is adapted to perform one or more of the following on the image:

selectively remove one or more color components

adjust image contrast;

invert colors;

blur;

sharpen the image;

or

zoom the image so that the image is scaled up using interpolation.

3. A test system according to claim 1, where the at least one filter includes a plurality of different filters and the filter configuration indicates which of the plurality of different filters are to be used to filter the image.

4. A test system according to claim 1, where each of the at least one filter has a plurality of different filter settings, and

where the filter configuration defines the plurality of different filter settings to be employed for filtering the image.

5. A test system according to claim 1, where the expected result is determined by optical character recognition.

6. A test system according to claim 1, where the processor, when obtaining the video frame, is to:

capture the video frame using a frame grabber.

7. A test system according to claim 1, wherein the device under test is one of:

a set-top box;

a digital media player;

or

a DVD player.

8. A test system according to claim 1, where the processor, when obtaining the video frame, is to:

acquire the video frame from display of the device under test using a camera.

9. A test system according to claim 8, where the device under test is one of:

a television;

a monitor;

a mobile telephone;

a personal digital assistant;

a digital camera;

or

a laptop.

19. A test system of claim 1, further comprising:

a remote control interface to transmit commands to the device under test.

10. A method comprising:

providing, by a device, a sequence of images of substantially a same content;

selecting, by the device, a filter configuration for a filter for pre-processing an image of the sequence of images, from a plurality of available filter configurations;

pre-processing, by the device, the image using the filter configuration to generate a pre-processed image;

submitting, by the device, the pre-processed image through optical character recognition (OCR) to extract text from the pre-processed image;

determining, by the device, a filter performance for the image based on comparing the text extracted from the pre-processed image to an expected text;

when the filter performance is a positive result, pre-processing, by the device, another image included in the sequence of images using the filter configuration;

when the filter performance is a negative result, repeatedly selecting, by the device, a different filter configuration and pre-processing the image using the different filter configuration until the positive result is determined; and

determining, by the device, a suitable filter configuration when the filter performance for each image in the sequence of images is positive for a same filter configuration.

11. A method according to claim 10, further comprising:

pre-processing each successive image in the sequence of images and performing the OCR on each successive image that is pre-processed as long as the text extracted from a preceding image is determined to be correct.

12. A method according to claim 10, further comprising:

pre-processing each image in the sequence of images;

performing the OCR on all of the images in the sequence that are pre-processed; and

where determining the suitable filter configuration includes determining whether the filter configuration is suitable when the text extracted from each of the images in sequence is determined to be correct.

13. A method according to claim 10, where

the filter configuration comprises one or more filter types selected from a plurality of different filter types.

14. A method according to claim 10, where the filter configuration comprises one or more parameters for the filter.

15. A method according to claim 10, where the filter comprises a plurality of sub-filters which are applied in combination, and

the filter configuration comprises one or more parameters for each of the plurality of sub-filters.

16. A non-transitory computer-readable storage medium storing instructions, the instructions comprising:

one or more instructions which, when executed by a processor, cause the processor to;

obtain a video frame, comprising images in sequence, from a device under test;

select a filter configuration for at least one filter to test;

filter an image included in the images in sequence using the filter configuration to generate a filtered image;

extract text from the filtered image using an optical character recognition (OCR) engine;

determine a filter performance for the image based on comparing the text extracted from the filtered image to an expected result;

when the filter performance is a positive result, filter another image included in the images in sequence using the filter configuration;

when the filter performance is a negative result, repeatedly select a different filter configuration and filter the image using the different filter configuration until the positive result is determined; and

determine a suitable filter configuration when the filter performance for each image in the images in sequence is positive for a same filter configuration.

17. A non-transitory computer-readable storage medium according to claim 16, where the at least one filter is adapted to perform one or more of the following on the image:

selectively remove one or more color components;

adjust image contrast;

invert colors;

blur;

sharpen the image;

or

zoom the image so that the image is scaled up using interpolation.

18. A non-transitory computer-readable storage medium according to claim 16, where the one or more instructions further cause the processor to:

transmit commands to the device under test via a remote control interface.