Liveness test method and apparatus and biometric authentication method and apparatus

1. A processor-implemented method, comprising:

generating a preprocessed infrared (IR) image by performing first preprocessing based on first feature points detected in a bounding region of an object included in an IR image;

generating a preprocessed depth image by performing second preprocessing based on second feature points detected in a bounding region of the object included in a depth image, the second feature points being detected by matching positions of the first feature points detected in the IR image to the depth image; and

determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image

wherein the generating of the preprocessed IR image comprises:

generating a first intermediate image based on pixel values of a current pixel and neighboring pixels of the current pixel in the IR image;

generating a second intermediate image by performing normalization on the IR image; and

generating the preprocessed IR image based on the IR image, the first intermediate image, and the second intermediate image.

2. The method of claim 1 , further comprising acquiring the IR image including the object and the depth image including the object.

3. The method of claim 1 , wherein the determining of whether the object is the genuine object comprises determining whether the object is an animate object.

4. The method of claim 1 , wherein the generating of the preprocessed IR image comprises generating the preprocessed IR image such that an edge component of the IR image is emphasized in the preprocessed IR image.

5. The method of claim 1 , wherein a pixel of the preprocessed IR image includes a pixel value of the current pixel in the IR image, a pixel value of a pixel at a corresponding position in the first intermediate image, and a pixel value of a pixel at a corresponding position in the second intermediate image.

6. The method of claim 1 , wherein the generating of the first intermediate image comprises combining a pixel value of the current pixel in the IR image and a pixel value of a pixel at a corresponding position in a generated single-channel IR image.

7. The method of claim 6 , wherein the generated single-channel IR image is generated by combining a pixel value of a pixel at the corresponding position in a first channel IR image, a pixel value of a pixel at the corresponding position in a second channel IR image, a pixel value of a pixel at the corresponding position in a third channel IR image, and a pixel value of a pixel at the corresponding position in a fourth channel IR image.

8. The method of claim 7 , wherein

the pixel value of the pixel in the first channel IR image is a pixel value of a pixel positioned immediately above the current pixel in the IR image,

the pixel value of the pixel in the second channel IR image is a pixel value of a pixel positioned immediately below the current pixel in the IR image,

the pixel value of the pixel in the third channel IR image is a pixel value of a pixel positioned immediately to the left of the current pixel in the IR image, and

the pixel value of the pixel in the fourth channel IR image is a pixel value of a pixel positioned immediately to the right of the current pixel in the IR image.

9. The method of claim 1 , wherein the generating of the preprocessed depth image comprises:

determining, as included in the second feature points detected in the depth image, third feature points of the object in the depth image; and

performing the second preprocessing by performing either one or both of a translation and a rotation of the object in the depth image based on the third feature points of the object.

10. The method of claim 1 , wherein the generating of the preprocessed depth image comprises:

determining, as included in the second feature points detected in the depth image, third feature points of the object in the depth image; and

performing the second preprocessing by transforming the object in the depth image into a frontal face based on the third feature points of the object and reference points of a predetermined face region.

11. The method of claim 10 , wherein the determining of the third feature points of the object comprises determining positions of the third feature points of the object in the depth image to correspond to positions of the first feature points, being of the object, detected in the IR image.

12. The method of claim 11 , wherein the performing of the second preprocessing comprises:

determining a transformation matrix based on the positions of the third feature points of the object in the depth image and corresponding positions of the reference points of the predetermined face region; and

applying the determined transformation matrix to the object in the depth image.

13. The method of claim 1 , wherein the determining of whether the object is a genuine object comprises:

determining a first liveness score by inputting the preprocessed IR image as an input to a neural network-based first liveness test model;

determining a second liveness score by inputting the preprocessed depth image to a neural network-based second liveness test model; and

determining whether the object is a genuine object based on the first liveness score and the second liveness score.

14. The method of claim 1 , wherein the determining of whether the object is a genuine object comprises:

determining a liveness score by inputting the preprocessed IR image and the preprocessed depth image to a neural network-based liveness test model; and

determining whether the object is a genuine object based on the liveness score.

15. The method of claim 1 , further comprising determining whether authentication of the object is successful based on the preprocessed IR image and the preprocessed depth image.

16. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the method of claim 1 .

17. A processor-implemented method, comprising:

generating a preprocessed infrared (IR) image by performing first preprocessing based on first feature points detected in a bounding region of an object included in an IR image;

generating a preprocessed depth image by performing second preprocessing based on second feature points detected in a bounding region of the object included in a depth image, the second feature points in the depth image being detected by matching positions of the first feature points detected in the IR image to the depth image; and

determining whether authentication of the object is successful based on the preprocessed IR image and the preprocessed depth image,

wherein the generating of the preprocessed IR image comprises:

generating a first intermediate image based on pixel values of a current pixel and neighboring pixels of the current pixel in the IR image;

generating a second intermediate image by performing normalization on the IR image; and

generating the preprocessed IR image based on the IR image, the first intermediate image, and the second intermediate image.

18. The method of claim 17 , further comprising acquiring the IR image including the object and the depth image including the object.

19. The method of claim 17 , wherein the generating of the preprocessed IR image comprises generating the preprocessed IR image such that an edge component of the IR image is emphasized in the preprocessed IR image.

20. The method of claim 17 , wherein the generating of the preprocessed IR image comprises:

generating a first intermediate image by performing edge emphasis on the IR image;

generating a second intermediate image by performing normalization on the IR image; and

generating the preprocessed IR image based on the IR image, the first intermediate image, and the second intermediate image.

21. The method of claim 20 , wherein the generating of the first intermediate image comprises generating the first intermediate image based on a pixel values of a current pixel and neighboring pixels of the current pixel in the IR image.

22. The method of claim 17 , wherein the generating of the preprocessed depth image comprises:

determining, as included in the second feature points detected in the depth image, third feature points of the object in the depth image; and

performing the second preprocessing by performing either one or both of a translation and a rotation of the object in the depth image based on the third feature points of the object.

23. The method of claim 17 , wherein the generating of the preprocessed depth image comprises:

determining, as included in the second feature points detected in the depth image, third feature points of the object in the depth image; and

performing the second preprocessing by transforming the object in the depth image into a frontal face based on the third feature points of the object and reference points of a predetermined face region.

24. The method of claim 17 , wherein the determining whether authentication of the object is successful comprises:

determining a first similarity between a first feature extracted from the preprocessed IR image and a first enrolled feature of a valid user;

determining a second similarity between a second feature extracted from the preprocessed depth image and a second enrolled feature of the valid user; and

determining whether authentication of the object is successful based on the first and second similarities.

25. The method of claim 17 , further comprising determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image.

26. An apparatus, comprising:

one or more image sensors configured to acquire an infrared (IR) image including an object and a depth image including the object; and

a processor configured to:

generate a preprocessed IR image by performing first preprocessing based on first feature points detected in a bounding region of an object included in the IR image,

generate a preprocessed depth image by performing second preprocessing based on second feature points detected in a bounding region of the object included in the depth image, the second feature points being detected by matching positions of the first feature points detected in the IR image to the depth image, and

determine either one or both of a liveness test result and an authentication result with respect to the object based on the preprocessed IR image and the preprocessed depth image,

wherein the generating of the preprocessed IR image comprises:

generating a first intermediate image based on pixel values of a current pixel and neighboring pixels of the current pixel in the IR image;

generating a second intermediate image by performing normalization on the IR image; and

generating the preprocessed IR image based on the IR image, the first intermediate image, and the second intermediate image.

27. The apparatus of claim 26 , wherein the processor is further configured to generate the preprocessed IR image such that an edge component of the IR image is emphasized in the preprocessed IR image.

28. The apparatus of claim 26 , wherein the processor is further configured to determine third feature points of the object in the depth image, and to perform the second preprocessing by transforming the object in the depth image into a frontal face based on the third feature points and reference points of a predetermined face region.

29. A processor-implemented method, comprising:

acquiring an infrared (IR) image including an object and a depth image including the object;

generating a preprocessed IR image by emphasizing an edge component of the IR image;

generating a preprocessed depth image by either one or both of translating and rotating the object in the depth image based on feature points detected in a bounding region of the object included in the depth image, the feature points in the depth image being detected by matching positions of feature points detected in a bounding region of the object included in the IR image to the depth image; and

determining either one or both of a liveness and a biometric authentication of the object based on the preprocessed IR image and the preprocessed depth image,

wherein the generating of the preprocessed IR image comprises:

generating a first intermediate image based on pixel values of a current pixel and neighboring pixels of the current pixel in the IR image;

generating a second intermediate image by performing normalization on the IR image; and

generating the preprocessed IR image based on the IR image, the first intermediate image, and the second intermediate image.