Multi-stage liveness determination
A method of determining whether a biometric object is part of a live individual is described. In one such method, image information is acquired from the biometric object by using a sensor, such as an ultrasonic sensor. The image information may be analyzed in at least two analysis stages. One of the analysis stages may be a temporal analysis stage that analyzes changes in the image information obtained during a time period throughout which the biometric object was continuously available to the sensor. For example, a dead/alive stage may analyze differences between image information taken at two different times in order to identify changes from one time to the next. Other stages may focus on aspects of a particular image information set, rather than seeking to assess changes over time. These other stages seek to determine whether an image information set exhibits characteristics similar to those of a live biometric object.
1. An apparatus, comprising:
an ultrasonic sensor configured for acquiring image information from an object using a plurality of ultrasonic frequencies;
a control system comprising one or more processors, the control system being configured for communication with the ultrasonic sensor, the control system being further configured for determining whether the object is part of a live individual, the control system being further configured for determining image quality of the image information, wherein the determining involves analyzing the image information in at least two analysis stages and wherein:
one of the analysis stages is a temporal analysis stage that involves analyzing changes in the image information acquired during a time period during which the object was available to the sensor; and
the other of the analysis stages involves analyzing the image information to determine whether the object includes at least one manufactured layer, wherein the analyzing involves evaluating the image quality of image information obtained from the object using the plurality of ultrasonic frequencies.
2. The apparatus of claim 1 , wherein the ultrasonic sensor is further configured for acquiring image information from the object using a plurality of range-gate delays.
3. The apparatus of claim 2 , wherein the control system is further configured for performing an image-fusion process on multiple instances of image information.
4. The apparatus of claim 3 , wherein each of the multiple instances of image information are acquired using at least one of a different ultrasonic frequency or a different range-gate delay.
5. The apparatus of claim 2 , wherein the control system is further configured for determining whether a number of pores at a surface of the object is greater than a number of pores at a depth within the object.
6. The apparatus of claim 1 , wherein the control system is further configured for determining whether the image quality is uniform or non-uniform.
7. The apparatus of claim 1 , wherein the control system is further configured for determining a fingerprint quality metric and wherein the fingerprint quality metric includes one or more metrics from a list of metrics consisting of spatial resolution, contrast, spatial frequency, pattern consistency, clarity and sharpness.
8. The apparatus of claim 7 , wherein the control system is further configured for:
selecting two or more blocks within a fingerprint image area;
applying a fingerprint quality metric to each block; and
determining a degree of variation in the fingerprint quality metric for each block.
9. The apparatus of claim 7 , wherein the fingerprint quality metric is clarity or sharpness.
10. The apparatus of claim 1 , wherein the control system is further configured to determine whether pattern types in the image information are among predetermined pattern types.
11. A method of determining whether an object is part of a live individual, comprising:
acquiring image information from the object using an ultrasonic sensor, wherein acquiring the image information involves a plurality of ultrasonic frequencies; and
analyzing the image information in at least two analysis stages, wherein one of the analysis stages is a temporal analysis stage that involves analyzing changes in the image information obtained during a time period during which the object was available to the sensor and the other of the analysis stages involves analyzing the image information to determine whether a number of pores at a surface of the object is greater than a number of pores at a depth within the object.
12. The method of claim 11 , wherein the temporal analysis stage involves determining whether a feature of the object changed during the time period.
13. The method of claim 12 , wherein the feature is selected from the group consisting of a pore opening size, a pore depth, a ridge pattern, and a texture.
14. The method of claim 11 , wherein the other of the analysis stages analyzes the image information to determine whether the object is three-dimensional.
15. The method of claim 14 , wherein determining whether the object is three-dimensional includes determining whether patterns of the object are uniform.
16. The method of claim 15 , wherein determining whether patterns of the object are uniform involves using a Sobel filter.
17. The method of claim 14 , further comprising concluding that the object is part of a live individual if:
(i) the temporal analysis stage indicates that a feature of the object changed during the time period; and
(ii) the other of the analysis stages indicates that the object is three-dimensional.
18. The method of claim 11 , wherein the other of the analysis stages involves analyzing the image information to determine whether pattern types in the image information are among predetermined pattern types.
19. The method of claim 11 , further comprising determining whether the object includes at least one manufactured layer, wherein determining whether the object includes at least one manufactured layer includes assessing image quality of the image information.
20. The method of claim 11 , wherein acquiring the image information involves a plurality of range-gate delays.
21. A non-transitory computer readable medium storing computer-executable code, the computer-executable code comprising instructions for:
acquiring image information from the object using an ultrasonic sensor, wherein acquiring the image information involves a plurality of ultrasonic frequencies; and
analyzing the image information in at least two analysis stages, wherein one of the analysis stages is a temporal analysis stage that involves analyzing changes in the image information obtained during a time period throughout which the object was continuously available to the sensor and the other of the analysis stages involves analyzing the image information to determine whether a number of pores at a surface of the object is greater than a number of pores at a depth within the object.
22. The medium of claim 21 , further comprising determining whether the object includes at least one manufactured layer, wherein determining whether the object includes at least one manufactured layer includes assessing image quality of the image information.
23. The medium of claim 21 , wherein the computer-executable code includes instructions for determining whether pattern types in the image information are among predetermined pattern types.
24. The medium of claim 21 , wherein acquiring the image information involves a plurality of range-gate delays.
25. An apparatus, comprising:
an ultrasonic sensor configured for acquiring image information from an object using a plurality of ultrasonic frequencies;
control means for determining whether the object is part of a live individual, wherein the determining involves analyzing the image information in at least two analysis stages and wherein:
one of the analysis stages is a temporal analysis stage that involves analyzing changes in the image information acquired during a time period during which the object was available to the sensor; and
the other of the analysis stages involves analyzing the image information to determine whether the object includes at least one manufactured layer, wherein the analyzing involves evaluating image quality of image information obtained from the object using the plurality of ultrasonic frequencies.
26. The apparatus of claim 25 , wherein the ultrasonic sensor is further configured for acquiring image information from the object using a plurality of range-gate delays.
27. The apparatus of claim 25 , wherein the control means includes means for:
selecting two or more blocks within a fingerprint image area;
applying a fingerprint quality metric to each block; and
determining a degree of variation in the fingerprint quality metric for each block.
28. The apparatus of claim 27 , wherein the fingerprint quality metric is clarity or sharpness.