Methods and systems for detecting biometric characteristics in an image
A method for detecting biometric characteristics in a captured biometric data image is provided that includes determining, by a processor, an approximate location for a biometric characteristic in a frame included in captured biometric data, and determining region of interest positions over the frame. Moreover, the method includes calculating a set of feature values for each position, generating a displacement for each set of feature values and generating a median displacement, and adjusting the biometric characteristic location by the median displacement.
1. A method for detecting biometric characteristics in a captured biometric data image comprising:
determining, by a processor, an approximate location for a biometric characteristic in a frame, the frame being included in captured biometric data;
determining region of interest positions over the frame;
calculating a set of feature values for each position;
generating a displacement for each set of feature values and generating a median displacement; and
adjusting the biometric characteristic location by the median displacement.
2. A method for detecting biometric characteristics in accordance with claim 1 , said determining region of interest positions step comprising:
centering a region of interest about the approximate location;
translating the region of interest such that the region of interest is not centered about the approximate location.
3. A method for detecting biometric characteristics in accordance with claim 1 , said calculating step comprising calculating a feature value for each combination of window type, window size, and window position listed in a look-up table.
4. A method for detecting biometric characteristics in accordance with claim 1 , said generating step comprising processing each feature value set with a first tree-based model and a second tree-based model, the first tree-based model generates a horizontal displacement and the second tree-based model generates a vertical displacement.
5. A method for detecting biometric characteristics in accordance with claim 1 , said generating step comprising calculating a median horizontal displacement and a median vertical displacement.
6. A system for detecting biometric characteristics in an image comprising:
a processor; and
a memory configured to store locations of a biometric characteristic, said processor being programmed to:
determine an approximate location for a biometric characteristic in a frame;
determine region of interest positions over the frame;
calculate a set of feature values for each position;
generate a displacement for each set of feature values and generate a median displacement; and
adjust the biometric characteristic location by the median displacement.
7. A system for detecting biometric characteristics in accordance with claim 6 , said processor being further programmed to:
center a region of interest about the approximate location;
translate the region of interest such that the region of interest is not centered about the approximate location.
8. A system for detecting biometric characteristics in accordance with claim 6 , said processor being further programmed to calculating a feature value for each combination of window type, window size, and window position listed in a look-up table.
9. A system for detecting biometric characteristics in accordance with claim 6 , said processor being further programmed to process each feature value set with a first tree-based model and a second tree-based model, the first tree-based model generates a horizontal displacement and the second tree-based model generates a vertical displacement.