Feature extraction and matching for biometric authentication
In a feature extraction and pattern matching system, image sharpening can enable vascular point detection (VPD) for detecting points of interest from visible vasculature of the eye. Pattern Histograms of Extended Multi-Radii Local Binary Patterns and/or Pattern Histograms of Extended Multi-Radii Center Symmetric Local Binary Patterns can provide description of portions of images surrounding a point of interest, and enrollment and verification templates can be generated using points detected via VPD and the corresponding descriptors. Inlier point pairs can be selected from the enrollment and verification templates, and a first match score indicating similarity of the two templates can be computed based on the number of inlier point pairs and one or more parameters of a transform selected by the inlier detection. A second match score can be computed by applying the selected transform, and either or both scores can be used to authenticate the user.
1. A computer-implemented method comprising:
receiving a verification template comprising a plurality of points of interest, each point of interest being associated with a plurality of different respective descriptors that each describe one or more localities surrounding the corresponding point of interest;
computing a match score for the verification template by comparing the verification template with one or more enrollment templates in a plurality of enrollment templates;
prior to computing the match score, ordering the plurality of enrollment templates according to respective exposure differences between a verification exposure template associated with the verification template and a respective enrollment exposure template associated with each enrollment template in the plurality of enrollment templates; and
adding the verification template to the plurality of enrollment templates based on, at least, the match score matching or exceeding an enrollment threshold.
2. The method of claim 1 , further comprising adjusting the match score according to (i) an exposure difference between the verification exposure template and an enrollment exposure template associated with one of the enrollment templates and/or (ii) an influence threshold.
3. The method of claim 2 , further comprising computing the exposure difference and/or an exposure similarity, based on at least one histogram measure.
4. The method of claim 1 , further comprising generating the verification exposure template and/or the enrollment exposure template.
5. The method of claim 4 , wherein generating the verification exposure template and/or the enrollment exposure template comprises:
partitioning a region of interest (ROI) of an image corresponding to the verification template into at least two sections; and
generating for each section a histogram of intensities representing, for each intensity in the histogram, a number of pixels in the section of the ROI having substantially that intensity.
6. The method of claim 5 , further comprising selecting the ROI by cropping an image of an eye according to a boundary of a scleral mask.
7. The method of claim 5 , further comprising selecting the ROI by cropping an image of an eye according to a boundary from one eye corner to another eye corner and from one eye lid to another eye lid.
8. The method of claim 4 , wherein generating the verification exposure template and/or the enrollment exposure template comprises generating a plurality of exposure measures.
9. A system comprising:
at least one processor; and
at least one memory for storing computer-executable instructions that, when executed by the at least one processor, program the at least one processor to perform the operations of:
receiving a verification template comprising a plurality of points of interest, each point of interest being associated with a plurality of different respective descriptors that each describe one or more localities surrounding the corresponding point of interest;
computing a match score for the verification template by comparing the verification template with one or more enrollment templates in a plurality of enrollment templates;
prior to computing the match score, ordering the plurality of enrollment templates according to respective exposure differences between a verification exposure template associated with the verification template and a respective enrollment exposure template associated with each enrollment template in the plurality of enrollment templates; and
adding the verification template to the plurality of enrollment templates based on, at least, the match score matching or exceeding an enrollment threshold.
10. The system of claim 9 , wherein the operations further comprise adjusting the match score according to (i) an exposure difference between the verification exposure template and an enrollment exposure template associated with one of the enrollment templates and/or (ii) an influence threshold.
11. The system of claim 10 , wherein the operations further comprise computing the exposure difference and/or an exposure similarity, based on at least one histogram measure.
12. The system of claim 9 , wherein the operations further comprise generating the verification exposure template and/or the enrollment exposure template.
13. The system of claim 12 , wherein generating the verification exposure template and/or the enrollment exposure template comprises:
partitioning a region of interest (ROI) of an image corresponding to the verification template into at least two sections; and
generating for each section a histogram of intensities representing, for each intensity in the histogram, a number of pixels in the section of the ROI having substantially that intensity.
14. The system of claim 13 , wherein the operations further comprise selecting the ROI by cropping an image of an eye according to a boundary of a scleral mask.
15. The system of claim 13 , wherein the operations further comprise selecting the ROI by cropping an image of an eye according to a boundary from one eye corner to another eye corner and from one eye lid to another eye lid.
16. The system of claim 12 , wherein generating the verification exposure template and/or the enrollment exposure template comprises generating a plurality of exposure measures.