Tracking surgical items with prediction of duplicate imaging of items

1. A computer-implemented method for tracking surgical textiles, comprising:

receiving a first image comprising a first textile-depicting image region;

receiving a second image comprising a second textile-depicting image region;

measuring a likelihood that the first and second image regions depict at least a portion of the same textile;

incrementing an index counter without requiring user confirmation, based on the likelihood not meeting a predetermined first threshold;

determining an image transformation between the first and second image regions;

adjusting the second image region relative to the first image region based on the image transformation;

displaying the first image region and the adjusted second image region on a display device,

incrementing the index counter, after providing notification and receiving user confirmation that the first and second images do not represent the same textile, based on the likelihood exceeding the predetermined first threshold but not exceeding a predetermined second threshold; and

not incrementing the index counter, despite receiving user input that the first and second images do not represent the same textile, based on the likelihood exceeding the predetermined second threshold.

2. The method of claim 1 , further comprising:

defining at least one classification feature at least partially based on at least one of a first aspect of the first image region and a second aspect of the second image region,

wherein the likelihood is based at least in part on the classification feature, wherein the first aspect comprises a plurality of first keypoints characterizing the first image region and the second aspect comprises a plurality of second key points characterizing the second image region, and wherein each of the first and second keypoints is associated with a respective feature descriptor.

3. The method of claim 2 , wherein defining at least one classification feature comprises fitting a homography transform relating the plurality of first keypoints and the plurality of second keypoints, and wherein the adjusting of the second image region relative to the first image region comprises applying the homography transform to one of the first image region or the second image region.

4. The method of claim 2 wherein at least one of the first and second aspects characterizes a fluid pattern.

5. The method of claim 1 wherein the image transformation flips the first image and the second image relative to each other.

6. The method of claim 1 wherein the image transformation rotates the first and second images relative to each other.

7. The method of claim 1 wherein the image transformation deskews the first and second images relative to each other.

8. The method of claim 1 , further comprising:

receiving user input relating to whether or not the first image region and second image region depict the same textile; and

based on the user input, either changing or not changing a textile count.

9. The method of claim 1 , further comprising:

incrementing the index counter despite the likelihood exceeding the predetermined second threshold after receiving additional user input confirming that the first and second images do not represent the same textile.

10. The method of claim 1 , further comprising displaying the index counter on a display.

11. A computer system comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, configure the computer system to performing operations comprising:

receiving a first image comprising a first textile-depicting image region;

receiving a second image comprising a second textile-depicting image region;

measuring a likelihood that the first and second image regions depict at least a portion of the same textile;

incrementing a textile count without requiring user confirmation, based on the likelihood not meeting a predetermined first threshold;

determining an image transformation between the first and second image regions;

adjusting the second image region relative to the first image region based on the image transformation;

displaying the first image region and the adjusted second image region on a display device;

incrementing the textile count, after providing notification and receiving user confirmation that the first and second images do not represent the same textile, based on the likelihood exceeding the predetermined first threshold but not exceeding a predetermined second threshold; and

not incrementing the textile count, despite receiving user input that the first and second images do not represent the same textile, based on the likelihood exceeding the predetermined second threshold.

12. The computer system of claim 11 , wherein the operations further comprise:

defining at least one classification feature at least partially based on at least one of a first aspect of the first image region and a second aspect of the second image region,

wherein the likelihood is based at least in part on the classification feature, wherein the first aspect comprises a plurality of first keypoints characterizing the first image region and the second aspect comprises a plurality of second key points characterizing the second image region, and wherein each of the first and second keypoints is associated with a respective feature descriptor.

13. The computer system of claim 12 , wherein defining at least one classification feature comprises fitting a homography transform relating the plurality of first keypoints and the plurality of second keypoints, and wherein the adjusting of the second image region relative to the first image region comprises applying the homography transform to one of the first image region or the second image region.

14. The computer system of claim 12 wherein at least one of the first and second aspects characterizes a fluid pattern.

15. The computer system of claim 11 , wherein the image transformation flips the first image and the second image relative to each other.

16. The computer system of claim 11 , wherein the image transformation rotates the first and second images relative to each other.

17. The computer system of claim 11 , wherein the image transformation deskews the first and second images relative to each other.

18. The computer system of claim 11 , wherein the operations further comprise:

receiving user input relating to whether or not the first image region and second image region depict the same textile; and

based on the user input, either changing or not changing a textile count.

19. The computer system of claim 11 , wherein the operations further comprise:

incrementing the textile count despite the likelihood exceeding the predetermined second threshold after receiving additional user input confirming that the first and second images do not represent the same textile.

20. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer system, cause the computer system to performing operations comprising:

receiving a first image comprising a first textile-depicting image region;

receiving a second image comprising a second textile-depicting image region;

measuring a likelihood that the first and second image regions depict at least a portion of the same textile;

incrementing a textile count without requiring user confirmation, based on the likelihood not meeting a predetermined first threshold;

determining an image transformation between the first and second image regions;

adjusting the second image region relative to the first image region based on the image transformation;

displaying the first image region and the adjusted second image region on a display device;

incrementing the textile count, after providing notification and receiving user confirmation that the first and second images do not represent the same textile, based on the likelihood exceeding the predetermined first threshold but not exceeding a predetermined second threshold; and

not incrementing the textile count, despite receiving user input that the first and second images do not represent the same textile, based on the likelihood exceeding the predetermined second threshold.

21. The computer-readable storage medium of claim 20 , wherein the operations further comprise:

defining at least one classification feature at least partially based on at least one of a first aspect of the first image region and a second aspect of the second image region,

wherein the likelihood is based at least in part on the classification feature, wherein the first aspect comprises a plurality of first keypoints characterizing the first image region and the second aspect comprises a plurality of second key points characterizing the second image region, and wherein each of the first and second keypoints is associated with a respective feature descriptor.

22. The computer-readable storage medium of claim 21 , wherein defining at least one classification feature comprises fitting a homography transform relating the plurality of first keypoints and the plurality of second keypoints, and wherein the adjusting of the second image region relative to the first image region comprises applying the homography transform to one of the first image region or the second image region.

23. The computer-readable storage medium of claim 21 wherein at least one of the first and second aspects characterizes a fluid pattern.

24. The computer-readable storage medium of claim 20 , wherein the image transformation flips the first image and the second image relative to each other.

25. The computer-readable storage medium of claim 20 , wherein the image transformation rotates the first and second images relative to each other.

26. The computer-readable storage medium of claim 20 , wherein the image transformation deskews the first and second images relative to each other.

27. The computer-readable storage medium of claim 20 , wherein the operations further comprise:

receiving user input relating to whether or not the first image region and second image region depict the same textile; and

based on the user input, either changing or not changing a textile count.

28. The computer-readable storage medium of claim 20 , wherein the operations further comprise:

incrementing the textile count despite the likelihood exceeding the predetermined second threshold after receiving additional user input confirming that the first and second images do not represent the same textile.