Gabor Filtering for Fingerprint Image Enhancement

Implementation from paper by Anil Jain - Fingerprint Image Enhancement Algorithm and Performance Evaluation

1. Gabor filter A gabor filter is a combination of a gaussian filter and a sinusoidal term. A gabor filter in 2 dimension is : X’ = xcos (theta) + ysin (theta); Y’ = - xsin (theta) + ycos (theta); The gaussian provides the weights and the sinusoidal provides the directionality.

2. Gaussian curve with a 2-dimensional domain

3. A Sinusoidal Wave (Magnitude) : Axes rotated by 45 degrees

4. Example of a two-dimensional Gabor filter

5. Feature extraction A set of Gabor filters with different frequencies and orientations may be helpful for extracting useful features from an image.

6. Use in Fingerprint enhancement Calculate Ridge orientation at every pixel

7. Estimate ridge frequency : generally fixed for a sensor ~0.2 considering its runtime and usefulness Apply gabor filter: block of 17X17 pixels

8. Move this Gabor filter with different orientations along the fingerprint

9. Reference : Fingerprint Image Enhancement: Algorithm and Performance Evaluation - Anil Jain

10. Thank you!!!