Automatic ruler detection

1. A method comprising:

obtaining an edge candidate group within an orientation map of an image that includes a fingerprint and a mensuration reference device, wherein edge pixels of the edge candidate group have a matching orientation;

identifying a set of regularity characteristics of the edge candidate group within the orientation map of the image that includes the fingerprint and the mensuration reference device;

determining that the set of regularity characteristics match a set of reference regularity characteristics associated with the mensuration reference device;

predicting a set of ruler marks from the edge candidate group based on the determining that the set of regularity characteristics match the set of reference regularity characteristics associated with the mensuration reference device; and

providing the set of ruler marks for output.

2. The method of claim 1 , further comprising:

computing an orientation histogram based on the orientation map;

identifying a plurality of matching orientations within an interval centered at a peak of the orientation histogram; and

generating a plurality of edge candidate groups using edge pixels corresponding to the identified plurality of matching orientations.

3. The method of claim 2 , wherein the interval centered at the peak of the orientation histogram is defined based at least on a number of orientations represented within the orientation map.

4. The method of claim 1 , wherein determining that the set of regularity characteristics match the set of reference regularity characteristics associated with the mensuration reference device comprises:

obtaining a plurality of descriptions for a ruler; and

determining that the edge candidate group includes a valid ruler based at least on the plurality of descriptions for the ruler.

5. The method of claim 1 , wherein predicting a set of ruler marks from the edge candidate group comprises:

estimating a ruler orientation described in the edge candidate group;

performing one or more regularity tests on the set of ruler marks the ruler orientation;

identifying one or more false marks within the set of rule marks based on performing the one or more regularity tests; and

removing the one or more false marks from the set of ruler marks.

6. The method of claim 1 , further comprising:

generating a gradient image of the image that includes a fingerprint and a mensuration reference device, wherein:

the gradient image comprises a plurality of pixels, and

each pixel included in the plurality of pixels is associated with a gradient value representing a respective change in pixel intensity of a corresponding pixel in the image with respect to neighboring pixels along an x-direction and neighboring pixels along a y-direction; and

wherein the orientation map is generated based on the gradient image.

7. The method of claim 6 , further comprising:

identifying a quality metric that defines a minimum level of gradient quality for the gradient image;

determining a gradient quality value associated with the gradient image; and

determining that the gradient value satisfies the quality metric.

8. A system comprising:

one or more computing devices; and

one or more storage devices storing instructions that, when executed by the one or more computing devices, cause the one or more computing devices to perform operations comprising:

obtaining an edge candidate group within an orientation map of an image that includes a fingerprint and a mensuration reference device, wherein edge pixels of the edge candidate group have a matching orientation;

identifying a set of regularity characteristics of the edge candidate group within the orientation map of the image that includes the fingerprint and the mensuration reference device;

determining that the set of regularity characteristics match a set of reference regularity characteristics associated with the mensuration reference device;

predicting a set of ruler marks from the edge candidate group based on the determining that the set of regularity characteristics match the set of reference regularity characteristics associated with the mensuration reference device; and

providing the set of ruler marks for output.

9. The system of claim 8 , wherein the operations further comprise:

computing an orientation histogram based on the orientation map;

identifying a plurality of matching orientations within an interval centered at a peak of the orientation histogram; and

generating a plurality of edge candidate groups using edge pixels corresponding to the identified plurality of matching orientations.

10. The system of claim 9 , wherein the interval centered at the peak of the orientation histogram is defined based at least on a number of orientations represented within the orientation map.

11. The system of claim 8 , wherein determining that the set of regularity characteristics match the set of reference regularity characteristics associated with the mensuration reference device comprises:

obtaining a plurality of descriptions for a ruler; and

determining that the edge candidate group includes a valid ruler based at least on the plurality of descriptions for the ruler.

12. The system of claim 8 , wherein predicting a set of ruler marks from the edge candidate group comprises:

estimating a ruler orientation described in the edge candidate group;

performing one or more regularity tests on the set of ruler marks the ruler orientation;

identifying one or more false marks within the set of rule marks based on performing the one or more regularity tests; and

removing the one or more false marks from the set of ruler marks.

13. The system of claim 8 , wherein the operations further comprise:

generating a gradient image of the image that includes a fingerprint and a mensuration reference device, wherein:

the gradient image comprises a plurality of pixels, and

each pixel included in the plurality of pixels is associated with a gradient value representing a respective change in pixel intensity of a corresponding pixel in the image with respect to neighboring pixels along an x-direction and neighboring pixels along a y-direction; and

wherein the orientation map is generated based on the gradient image.

14. The system of claim 13 , wherein the operations further comprise:

identifying a quality metric that defines a minimum level of gradient quality for the gradient image;

determining a gradient quality value associated with the gradient image; and

determining that the gradient value satisfies the quality metric.

15. At least one non-transitory computer-readable storage device encoded with instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:

obtaining an edge candidate group within an orientation map of an image that includes a fingerprint and a mensuration reference device, wherein edge pixels of the edge candidate group have a matching orientation;

identifying a set of regularity characteristics of the edge candidate group within the orientation map of the image that includes the fingerprint and the mensuration reference device;

determining that the set of regularity characteristics match a set of reference regularity characteristics associated with the mensuration reference device;

predicting a set of ruler marks from the edge candidate group based on the determining that the set of regularity characteristics match the set of reference regularity characteristics associated with the mensuration reference device; and

providing the set of ruler marks for output.

16. The non-transitory computer-readable storage device of claim 15 , wherein the operations further comprise:

computing an orientation histogram based on the orientation map;

identifying a plurality of matching orientations within an interval centered at a peak of the orientation histogram; and

generating a plurality of edge candidate groups using edge pixels corresponding to the identified plurality of matching orientations.

17. The non-transitory computer-readable storage device of claim 16 , wherein the interval centered at the peak of the orientation histogram is defined based at least on a number of orientations represented within the orientation map.

18. The non-transitory computer-readable storage device of claim 15 , wherein determining that the set of regularity characteristics match the set of reference regularity characteristics associated with the mensuration reference device comprises:

obtaining a plurality of descriptions for a ruler; and

determining that the edge candidate group includes a valid ruler based at least on the plurality of descriptions for the ruler.

19. The non-transitory computer-readable storage device of claim 15 , wherein predicting a set of ruler marks from the edge candidate group comprises:

estimating a ruler orientation described in the edge candidate group;

performing one or more regularity tests on the set of ruler marks the ruler orientation;

identifying one or more false marks within the set of rule marks based on performing the one or more regularity tests; and

removing the one or more false marks from the set of ruler marks.

20. The non-transitory computer-readable storage device of claim 15 , wherein the operations further comprise:

generating a gradient image of the image that includes a fingerprint and a mensuration reference device, wherein:

the gradient image comprises a plurality of pixels, and

each pixel included in the plurality of pixels is associated with a gradient value representing a respective change in pixel intensity of a corresponding pixel in the image with respect to neighboring pixels along an x-direction and neighboring pixels along a y-direction; and

wherein the orientation map is generated based on the gradient image.