Image processing method and system for iris recognition

1. A method of iris recognition, comprising:

detecting a body region comprising at least one iris of an eye in an image acquired by an image sensor;

performing a first iris recognition of the iris based on a first portion of the image;

in response to the first iris recognition failing, performing a second iris recognition, the second iris recognition comprising a first iris identification on the image based on a second portion of the image smaller than the first portion of the image;

in response to the second iris recognition failing, performing a third iris recognition, the third iris recognition comprising a second iris identification on the image, wherein the second iris identification is based on a third portion of the image larger than the first portion of the image; and

outputting a result of the second iris identification.

2. The method of claim 1 , wherein:

the first iris recognition comprises:

identifying a first plurality of cardinal points around the eye based on a first eye modeling of the first portion of the image;

performing a first iris segmentation to identify a first segment of the iris within the first portion of the image based on the first plurality of cardinal points; and

determining that a first confidence score associated with the first segment is less than a first threshold;

the second iris recognition is performed based at least in part on the determination that the first confidence score is less than the first threshold, the second iris recognition comprising:

identifying a second plurality of cardinal points around the eye based on a second eye modeling of the second portion of the image;

performing a second iris segmentation to identify a second segment of the iris within the second portion of the image based on the second plurality of cardinal points; and

determining that a second confidence score is less than a second threshold,

the third iris recognition is performed based at least in part on the determination that the second confidence score is less than the second threshold.

3. The method of claim 2 , further comprising:

identifying a third plurality of cardinal points around the eye based on a third eye modeling of the third portion of the image;

performing a third iris segmentation to identify a third segment of the iris within the third portion of the image based on the third plurality of cardinal points;

determining that a third confidence score associated with the third segment is less than a third threshold; and

determine that the third iris segmentation failed based at least in part on the determination that the third confidence score is less than the third threshold.

4. The method of claim 3 , wherein the first segment, the second segment, and the third segment are each defined by an inner perimeter and an outer perimeter.

5. The method of claim 3 , wherein the first confidence score, the second confidence score, and the third confidence score are based on at least one of the first segment, the second segment, or the third segment, respectively, or an iris code extracted from the first segment, the second segment, or the third segment, respectively.

6. The method of claim 3 , comprising:

in response to the third confidence score being above the third threshold, identifying a subject of the image based on a result of the third segment.

7. The method of claim 3 , further comprising, in response to the third confidence score being less than the third threshold:

selecting a highest confidence score from among the first confidence score, the second confidence score, and the third confidence score; and

selecting a segment from among the first segment, the second segment, and the third segment that produced the highest confidence score from which an iris code is extracted.

8. The method of claim 3 , further comprising, in response to the third confidence score being less than the third threshold, indicating that the iris is not detectable within the image.

9. The method of claim 3 , wherein at least one of the first confidence score, the second confidence score, or the third confidence score is based on at least one of:

a portion of the iris that is visible in the image,

an illumination level of the iris in the image,

a precision with which an internal perimeter of the iris is determined,

a precision with which an external perimeter of the iris is determined,

a number of classifier scales used to detect the iris,

a number of image locations used to detect the iris,

a precision of a classifying of the iris,

a focus level of the image,

a level of contrast within the image,

a size of an iris segment, or

a contrast level of the iris segment.

10. The method of claim 3 , wherein the third portion of the image comprises a whole of the image.

11. The method of claim 2 , wherein the first plurality of cardinal points and the second plurality of cardinal points are different.

12. The method of claim 1 , wherein detecting the body region in the image comprises performing at least one of a face detection or an eye detection.

13. A non-transitory computer readable medium storing instructions to, when executed by a processing unit:

detect a body region comprising an iris of an eye in an image acquired by an image sensor;

perform a first iris recognition of the iris based on a first portion of the image;

in response to the first iris recognition succeeding, identify a subject of the image;

in response to the first iris recognition failing, perform a second iris recognition, the second iris recognition comprising a first iris identification on the image based on a second portion of the image smaller than the first portion of the image;

in response to the second iris recognition succeeding, identify the subject of the image;

in response to the second iris recognition failing, perform a third iris recognition, the third iris recognition comprising a second iris identification on the image, wherein the second iris identification is based on a third portion of the image larger than to the first portion of the image; and

output a result of the second iris identification.

14. The non-transitory computer readable medium of claim 13 , further comprising instructions to, when executed by a processing unit:

in response to the third iris recognition failing:

determine which of the first iris recognition, the second iris recognition, or the third iris recognition produced a highest confidence level; and

extract an iris code for the image using the one of the first iris recognition, the second iris recognition, or the third iris recognition with the highest confidence level.

15. The non-transitory computer readable medium of claim 13 , further comprising instructions to, when executed by the processing unit:

in response to the third iris recognition failing, return an indication that the iris is not detectable within the image.

16. An image processing system for iris recognition comprising:

an image sensor to acquire an image; and

a processor to execute instructions stored on a non-transitory computer readable medium to, when executed:

detect a body region comprising an iris of an eye in the image;

perform a first iris recognition of the iris based on a first portion of the image;

in response to the first iris recognition failing, perform a second iris recognition, the second iris recognition comprising a first iris identification on the image based on a second portion of the image smaller than the first portion of the image; and

in response to the second iris recognition failing, perform a third iris recognition, the third iris recognition comprising a second iris identification on the image, wherein the second iris identification is based on a third portion of the image larger than the first portion of the image; and

output a result of the second iris identification.

17. The image processing system of claim 16 , wherein:

the first iris recognition comprises:

identifying a first plurality of cardinal points around the eye based on a first eye modeling of the first portion of the image;

performing a first iris segmentation to identify a first segment of the iris within the first portion of the image based on the first plurality of cardinal points; and

determining that a first confidence score is less than a first threshold;

the second iris recognition is performed based at least in part on the determination that the first confidence score is less than the first threshold, the second iris recognition comprising:

identifying a second plurality of cardinal points around the eye based on a second eye modeling of the second portion of the image;

performing a second iris segmentation to identify a second segment of the iris within the second portion of the image based on the second plurality of cardinal points; and

determining that a second confidence score is less than a second threshold;

the third iris recognition is performed based at least in part on the determination that the second confidence score is less than the second threshold, the third iris recognition comprising:

identify a third plurality of cardinal points around the eye based on a third eye modeling of the third portion of the image;

perform a third iris segmentation to identify a third segment of the iris within the third portion of the image based on the third plurality of cardinal points;

determine that a third confidence score associated with the third segment is less than a third threshold; and

in response to the third confidence score being less than the third threshold, indicating that the iris is not detectable within the image.

18. The image processing system of claim 17 , wherein the first plurality of cardinal points identified in the first portion of the image are different from the second plurality of cardinal points identified in the second portion of the image.

19. The image processing system of claim 17 , wherein outputting the result of the second iris identification comprises at least one of:

indicating that the iris is not detectable within the image,

identifying a subject of the image based on a result of the third segment in response to the third confidence score being above the third threshold, or

identifying the subject of the image based on a foremost segment from among the first segment, the second segment, and the third segment that produced a highest confidence score from which an iris code is extracted in response to the third confidence score being less than the third threshold.

20. The image processing system of claim 16 , wherein:

the third portion of the image comprises a whole of the image.