Semi-automated system for real-time wound image segmentation and photogrammetry on a mobile platform

1. A mobile device, comprising:

a user input; and

a processor;

wherein the processor is configured to:

receive a wound image;

wherein the processor and user input are configured to:

receive an input from a user defining an initial outline of a wound;

wherein the processor is configured to:

identify features of the wound image on opposing sides of the initial outline of the wound, and

calculate an actual perimeter of the wound based on the initial outline of the wound and the identified features of the wound image.

2. The mobile device of claim 1 , further comprising:

a display screen;

wherein the processor and display screen are configured to:

display a graphical representation of the actual perimeter of the wound.

3. The mobile device of claim 1 , wherein the processor is configured to:

calculate a wound area based on the actual perimeter of the wound.

4. The mobile device of claim 3 , wherein the processor is configured to:

identify a number of pixels enclosed by the actual perimeter of the wound;

detect an image scale-identification marker present in the wound image;

identify a size of each pixel based on the image scale-identification marker; and

calculate a wound area based on the number of pixels enclosed by the actual perimeter of the wound.

5. The mobile device of claim 1 , wherein the processor is configured to:

initialize an active contour model by defining the initial outline of the wound as an initial active contour;

perform an iterative energy minimization process on the initial active contour to determine a final active contour; and

storing the final active contour as the actual perimeter of the wound.

6. The mobile device of claim 5 , wherein the processor is configured to:

convert the wound image from an RGB color space to a CMYK color space; and

decompose the wound image into a magenta component and a yellow component.

7. The mobile device of claim 6 , wherein the processor is configured to:

define the magenta component as a low-energy state in the iterative energy minimization process.

8. The mobile device of claim 6 , wherein the processor is configured to:

define the yellow component as a low-energy state in the iterative energy minimization process.

9. The mobile device of claim 1 , wherein the processor is configured to:

create a gradient image in an x-direction from the wound image.

10. The mobile device of claim 9 , wherein the processor is configured to:

calculate the actual perimeter of the wound by identifying areas of high gradient from the gradient image.

11. The mobile device of claim 1 , wherein the processor is configured to:

create a gradient image in a y-direction from the wound image.

12. The mobile device of claim 11 , wherein the processor is configured to:

calculate the actual perimeter of the wound by identifying areas of high gradient from the gradient image.

13. A wound imaging method, comprising:

receiving, at a mobile device, a wound image;

receiving, at the mobile device, an input from a user defining an initial outline of a wound;

identifying, at a processor of the mobile device features of the wound image on opposing sides of the initial outline of the wound image; and

calculating, at the processor, an actual perimeter of the wound based on the initial outline of the wound and the identified features of the wound image.

14. The method of claim 13 , further comprising:

displaying, on a screen of the mobile device, a graphical representation of the actual perimeter of the wound.

15. The method of claim 13 , further comprising:

calculating, at the processor, a wound area based on the actual perimeter of the wound.

16. The method of claim 13 , wherein the calculating step further comprises:

identifying a number of pixels enclosed by the actual perimeter of the wound;

detecting an image scale-identification marker present in the wound image;

identifying a size of each pixel based on the image scale-identification marker; and

calculating a wound area based on the number of pixels enclosed by the actual perimeter of the wound.

17. The method of claim 13 , wherein the calculating step further comprises:

initializing an active contour model by defining an initial outline of the wound as an initial active contour;

performing an iterative energy minimization process on the initial active contour to determine a final active contour; and

storing the final active contour as the actual perimeter of the wound.

18. The method of claim 17 , wherein the calculating step further comprises:

converting the wound image from an RGB color space to a CMYK color space;

decomposing the wound image into a magenta component; and

defining the magenta component as a low-energy state in the iterative energy minimization process.

19. The method of claim 17 , wherein the calculating step further comprises:

converting the wound image from an RGB space to a CYMK color space;

decomposing the wound image into a yellow component; and

defining the yellow component as a low-energy state in the iterative energy minimization process.

20. The method of claim 13 , wherein the calculating step further comprises:

creating a gradient image from the wound image; and

calculating the actual perimeter of the wound by identifying areas of high gradient from the gradient image.