Methods and apparatus to capture photographs using mobile devices

• US 10,136,052 B2
• Filed: 01/15/2018
• Issued: 11/20/2018
• Est. Priority Date: 06/18/2015
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Garcia Morate, Diego, Hurtado Gacia, Antonio, Tovar Velasco, Javier, Barrales Ruiz, Carlos
• Primary Examiner(s): Chen, Chia-Wei A
• Application Number:
  US15/871,658
• Publication Number:
  US 20180139381A1
• Time in Patent Office: 309 Days
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 3/4038 Image mosaicing, e.g. composing plane images from plane sub-images
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/16 using multiple overlapping images; Image stitching
• CPC Class Codes: G06V 10/17 using hand-held instruments
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: H04N 23/635 Region indicators; Field of view indicators
• CPC Class Codes: H04N 23/64 Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
• CPC Class Codes: H04N 23/6811 based on the image signal

Abstract

Methods and apparatus to capture photographs using mobile devices are disclosed. An example apparatus includes a photograph capturing controller to capture a photograph with a mobile device. the example apparatus further includes a perspective analyzer, implemented by the mobile device, to analyze the photograph to determine a probability of perspective being present in the photograph. The example apparatus also includes a photograph capturing interface to prompt a user to capture a new photograph when the probability of perspective exceeds a threshold.

Claims

1. An apparatus comprising:

a photograph capturing controller to capture a photograph with a mobile device;

a perspective analyzer, implemented by the mobile device, to analyze the photograph to determine a probability of perspective being present in the photograph by;

applying an edge detection filter to the photograph to determine edge pixels corresponding to edges identified by the edge detection filter within the photograph;

evaluating potential edge lines passing through a first one of the edge pixels;

determining a first one of the potential edge lines that passes through more of the edge pixels than other ones of the potential edge lines; and

calculating the probability of perspective based on an angle of the first one of the potential edge lines; and

a photograph capturing interface to prompt a user to capture a new photograph when the probability of perspective exceeds a threshold.

2. The apparatus of claim 1, wherein a quantity of the edge pixels through which the potential edge lines pass through is normalized by a length of respective ones of the potential edge lines, the length of the respective ones of potential edge lines defined by a perimeter of the photograph.

3. The apparatus of claim 1, wherein the perspective analyzer is to calculate a second one of the potential edge lines for a second one of the edge pixels and to calculate the probability of perspective based on a difference in angles of the first and second ones of the potential edge lines.

4. The apparatus of claim 3, wherein the perspective analyzer is to divide the photograph into separate areas, the first edge pixel corresponding to a first one of the areas and the second edge pixel corresponding to a second one of the areas.

5. The apparatus of claim 4, wherein the separate areas extend across an entire width of the photograph in a horizontal direction.

6. The apparatus of claim 1, wherein the perspective analyzer is to calculate the probability of perspective by applying a logistic model to a plurality of angles corresponding to a plurality of lines identified for a plurality of areas of the photograph, the plurality of lines including the first one of the potential edge lines.

7. The apparatus of claim 1, wherein the perspective analyzer is to generate the potential edge lines by:

determining a series of lines passing through the first edge pixel at different angles between a range of angles within a threshold angle of a line extending perpendicular to a direction of the edge detection filter; and

defining end points for each line in the series of lines based on a size of the photograph.

8. The apparatus of claim 1, wherein the edge detection filter is applied in a vertical direction such that at least some of the edges identified by the edge detection filter correspond to a horizontal shelf of a shelving module captured in the photograph.

9. A non-transitory computer readable medium comprising instructions that, when executed, causes a processor to at least:

capture a photograph with a mobile device;

determine a probability of perspective being present in the photograph by;

applying an edge detection filter to the photograph to determine edge pixels corresponding to edges identified by the edge detection filter within the photograph;

evaluating potential edge lines passing through a first one of the edge pixels;

determining a first one of the potential edge lines that passes through more of the edge pixels than other ones of the potential edge lines; and

calculating the probability of perspective based on an angle of the first one of the potential edge lines; and

prompt a user to capture a new photograph when the probability of perspective exceeds a threshold.

10. The non-transitory computer readable medium of claim 9, wherein the instructions further cause the processor to normalize a quantity of the edge pixels through which the potential edge lines pass through based on a length of respective ones of the potential edge lines, the length of the respective ones of the potential edge lines defined by a perimeter of the photograph.

11. The non-transitory computer readable medium of claim 9, wherein the instructions further cause the processor to calculate a second one of the potential edge lines for a second one of the edge pixels and to calculate the probability of perspective based on a difference in angles of the first and second ones of the potential edge lines.

12. The non-transitory computer readable medium of claim 11, wherein the instructions further cause the processor to divide the photograph into separate areas, the first edge pixel corresponding to a first one of the areas and the second edge pixel corresponding to a second one of the areas.

13. The non-transitory computer readable medium of claim 9, wherein the instructions further cause the processor to calculate the probability of perspective by applying a logistic model to a plurality of angles corresponding to a plurality of best lines identified for a plurality of areas of the photograph.

14. The non-transitory computer readable medium of claim 9, wherein the instructions further cause the processor to generate the potential edge lines by:

determining a series of lines passing through the first edge pixel at different angles between a range of angles within a threshold angle of a line extending perpendicular to a direction of the edge detection filter; and

defining end points for each line in the series of lines based on a size of the photograph.

15. The non-transitory computer readable medium of claim 9, wherein the edge detection filter is applied in a vertical direction such that at least some of the edges identified by the edge detection filter correspond to a horizontal shelf of a shelving module captured in the photograph.

16. A method comprising:

capturing a photograph with a mobile device;

determining, by executing an instruction with a processor, a probability of perspective being present in the photograph by;

applying an edge detection filter to the photograph to determine edge pixels corresponding to edges identified by the edge detection filter within the photograph;

evaluating potential edge lines passing through a first one of the edge pixels;

determining a first one of the potential edge lines that passes through more of the edge pixels than other ones of the potential edge lines; and

calculating the probability of perspective based on an angle of the first one of the potential edge lines; and

prompting, by executing an instruction with the processor, a user to capture a new photograph when the probability of perspective exceeds a threshold.

17. The method of claim 16, further including generating the potential edge lines by:

determining a series of lines passing through the first edge pixel at different angles between a range of angles within a threshold angle of a line extending perpendicular to a direction of the edge detection filter; and

defining end points for each line in the series of lines based on a size of the photograph.