Methods and apparatus to capture photographs using mobile devices
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.
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.