Blurring based content recognizer

• US 8,929,676 B2
• Filed: 04/30/2009
• Issued: 01/06/2015
• Est. Priority Date: 01/27/2009
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: van der Merwe, Rudolph, Crandall, Richard Eugene, Noble, Samuel Gordon, Serlet, Bertrand, Kounitski, Stanislav
• Primary Examiner(s): Park, Chan
• Assistant Examiner(s): Thomas, Mia M
• Application Number:
  US12/433,120
• Publication Number:
  US 20100189367A1
• Time in Patent Office: 2,077 Days
• Field of Search: 382/101, 382/107, 382168-173, 382/181, 382/195, 382/228, 382/229, 382/254, 382/255, 382/280, 725/118, 725/119, 348345-357
• US Class Current: 382/255
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06V 30/2247 Characters composed of bars, e.g. CMC-7

Abstract

Methods, systems, and apparatus, including computer program products, for identifying regions of interest in an image and identifying a barcode in a degraded image are provided. A region of interest is identified by pre-processing an image, generating a binary image based on a metric calculated on the pre-processed image, and analyzing regions of the image identified using connected components and other analysis. A barcode is identified by searching a population of barcodes, degrading ideal image intensity profiles of candidate barcodes, and comparing the degraded ideal image intensity profiles to an image intensity profile of the degraded image.

Claims

1. A computer implemented method, comprising:

receiving a degraded image of a first object of interest;

determining, in a computer, a representation of a feature of the degraded image;

searching a population of objects using a genetic algorithm, where the genetic algorithm includes using the computer to calculate a fitness score for a candidate object using a fitness function that compares the representation of the feature of the degraded image to a degraded representation of a feature of a non-degraded image of the candidate object; and

selecting a second object of interest corresponding to the first object of interest as a result of the searching.

2. The method of claim 1, further comprising:

identifying a region of interest in the degraded image, where the region of interest contains the first object of interest; and

wherein determining the representation of the feature of the degraded image includes determining a representation of a feature of the region of interest.

3. The method of claim 1, further comprising:

receiving context information about the degraded image; and

wherein the searching is biased based on the context information.

4. The method of claim 1, further comprising:

receiving data for the device used to capture the degraded image;

generating, in the computer, a blur kernel corresponding to the degraded image using the received data; and

determining the degraded representation of the feature of the non-degraded image of the candidate object using the blur kernel.

5. The method of claim 4, wherein:

the data is accelerometer data for the device; and

the blur kernel is a motion blur kernel.

6. The method of claim 5, wherein the data is calibration data.

7. A computer implemented method, comprising:

receiving a degraded image of a first object of interest;

determining, in a computer, a representation of a feature of the degraded image;

searching a population of objects, the searching including identifying a current population of candidate objects and repeating the following one or more times in the computer;

for each candidate object in the current population;

determining a degraded representation of a feature of a non-degraded image of the candidate object; and

calculating a fitness score comparing the degraded representation to the representation of the feature of the degraded image; and

updating the current population using the calculated fitness score for each candidate object; and

selecting a second object of interest corresponding to the first object of interest from the population of objects based on the calculated fitness scores.

8. The method of claim 7, further comprising:

identifying a region of interest in the degraded image, where the region of interest contains the first object of interest; and

wherein determining the representation of the feature of the degraded image includes determining a representation of a feature of the region of interest.

9. The method of claim 7, further comprising:

receiving context information about the degraded image; and

using the context information when identifying the current population of candidate objects.

10. The method of claim 7, further comprising:

receiving accelerometer data regarding a device used to capture the degraded image;

estimating a motion blur in the degraded image using the accelerometer data; and

determining the degraded representation of the feature of the non-degraded image of the candidate object using the estimated motion blur.

11. The method of claim 7, further comprising:

receiving calibration information; and

determining the degraded representation of the feature of the non-degraded image of the candidate object using the calibration information.

12. A computer implemented method, comprising:

receiving a degraded image of a first object of interest;

pre-processing the degraded image using a computer, resulting in a pre-processed image;

calculating, in the computer, a metric based on the pre-processed image;

generating, in the computer, a binary image from the pre-processed image based on the metric;

identifying one or more regions of the binary image using connected components analysis;

selecting a region of interest in the degraded image based on an analysis of the identified regions of the binary image, where the region of interest includes the first object of interest;

generating, in the computer, a representation of a feature of the refined region of interest;

searching a population of objects, the searching including identifying a current population of candidate objects and repeating the following steps one or more times in the computer;

for each candidate object in the current population;

determining a degraded representation of a feature of a non-degraded image of the candidate object; and

calculating a fitness score comparing the degraded representation to the representation of the feature of the degraded image; and

updating the current population using the calculated fitness scores; and

selecting a second object of interest corresponding to the first object of interest from the population of objects based on the calculated fitness scores.

13. The computer implemented method of claim 12, further comprising using a probabilistic cost function to refine the region of interest.

14. The method of claim 12, further comprising:

receiving context information about the degraded image; and

wherein the searching is biased based on the context information.

15. A system, comprising:

a processor; and

a computer-readable medium coupled to the processor and including instructions, which, when executed by the processor, causes the processor to perform operations comprising;

receiving a degraded image of a first object of interest from a client device;

determining a representation of a feature of the degraded image;

searching a population of objects using a genetic algorithm, where the genetic algorithm includes calculating a fitness score for a candidate object using a fitness function that compares the representation of the feature of the degraded image to a degraded representation of a feature of a non-degraded image of the candidate object; and

selecting a second object of interest corresponding to the first object of interest as a result of the searching, and sending the selected second object of interest to the client device.

16. The system of claim 15, wherein the system comprises a server and the client device is a mobile device.

17. The system of claim 15, wherein the processor further performs operations comprising:

identifying a region of interest in the degraded image, where the region of interest contains the first object of interest; and

wherein determining the representation of the feature of the degraded image includes determining a representation of a feature of the region of interest.

18. The system of claim 15, wherein the processor further performs operations comprising:

receiving accelerometer data regarding a device used to capture the degraded image;

estimating a motion blur in the degraded image using the accelerometer data; and

determining the degraded representation of the feature of the non-degraded image of the candidate object using the estimated motion blur.

19. A computer program product encoded on a tangible, non-transitory storage medium, the product comprising computer readable instructions for causing one or more processors to perform operations comprising:

receiving a degraded image of a first object of interest;

determining a representation of a feature of the degraded image;

searching a population of objects using a genetic algorithm, where the genetic algorithm includes calculating a fitness score for a candidate object using a fitness function that compares the representation of the feature of the degraded image to a degraded representation of a feature of a non-degraded image of the candidate object; and

selecting a second object of interest corresponding to the first object of interest as a result of the searching.

20. The computer program product of claim 19, further having instructions stored thereon which, when executed by the processor, causes the processor to perform operations comprising:

identifying a region of interest in the degraded image, where the region of interest contains the first object of interest; and

wherein determining the representation of the feature of the degraded image includes determining a representation of a feature of the region of interest.

21. The computer program product of claim 19, further having instructions stored thereon which, when executed by the processor, causes the processor to perform operations comprising:

receiving context information about the degraded image; and

wherein the searching is biased based on the context information.

22. The computer program product of claim 19, further having instructions stored thereon which, when executed by the processor, causes the processor to perform operations comprising:

receiving accelerometer data regarding a device used to capture the degraded image;

estimating a motion blur in the degraded image using the accelerometer data; and

determining the degraded representation of the feature of the non-degraded image of the candidate object using the estimated motion blur.