Slap segmentation of contactless fingerprint images

1. A method to segment slap images and to generate accurately labelled individual fingerprints, said method comprising the following steps:

reception of inputs images from a contactless fingerprint reader under controlled lighting conditions;

computation of a variance in the received images to estimate a slap area as a foreground slap mask in the input images;

identification of individual fingers by finding boundary of each finger by an adaptive binarization sub step applied to an original lighted image with the foreground slap mask by calculating the dynamic range of both global and local dynamics according to the equation Thres(x,y)=α(x,y)+pα(x,y)(β(x,y)−q), where α(x,y) is a local dynamic factor, β(x,y) is a global dynamic factor and p,q are pre-defined parameters, this adaptive binarization sub step outputting individual finger's masks;

verification of a number of fingers and of geometric constraints;

calculation of pose and orientation based on shape and geometry information;

identification of effective fingertip area on each detected finger according the pose, orientation, as well as geometric information;

output of individual fingerprints.

2. The method to segment slap images according to claim 1 , wherein the images acquired under controlled lighting conditions are images acquired with and without flash light.

3. The method to segment slap images according to claim 1 , wherein the step of calculation of pose and orientation based on shape and geometry information comprises a convexity check to detect fingertip points of the fingers.

4. The method to segment slap images according to claim 1 , wherein the step of calculation of pose and orientation based on shape and geometry information comprises a sub step of defining a center line of each individual finger mask, a sub step of calculating gradients along the direction of the finger centerline on the finger image, a sub step of detection of a first finger joint by finding perpendicular line with maximum gradient within certain distance to a fingertip point, a fingertip mask being defined by the area extending between the first finger joint and the fingertip point.

5. A contactless acquired fingerprint image processor connected to at least a contactless fingerprint reader having various lighting conditions and adapted to acquire images of slap/fingers in a contactless position in vicinity of the reader under different lighting conditions for the acquisition of fingerprints of a user, said processor being adapted to segment slap images received from a contactless fingerprint reader under controlled lighting conditions and to generate accurately labelled individual fingerprints, said processor being adapted to compute a variance in the received images to estimate a slap area as a foreground slap mask in the input images, to identify individual fingers by finding boundary of each finger by being adapted to perform an adaptive binarization applied to an original lighted image with the foreground slap mask by calculating the dynamic range of both global and local dynamics according to the equation Thres(x,y)=α(x,y)+pα(x,y)(β(x,y)−q), where α(x,y) is a local dynamic factor, β(x,y) is a global dynamic factor and p, q are pre-defined parameters, this adaptive binarization sub step outputting individual finger's masks, to verify a number of fingers and of geometric constraints, to calculate pose and orientation based on shape and geometry information, identification of effective fingertip area on each detected finger according the pose, orientation, as well as geometric information, output of individual fingerprints.

6. The contactless acquired fingerprint image processor according to claim 5 , said processor being adapted to calculate pose and orientation based on shape and geometry information using a convexity check to detect fingertip points of the fingers.

7. The contactless acquired fingerprint image processor according to claim 5 , said processor being adapted to calculate pose and orientation based on shape and geometry information including a definition of a center line of each individual finger mask, a calculation of gradients along the direction of the finger centerline on the finger image, a detection of a first finger joint by finding perpendicular line with maximum gradient within certain distance to a fingertip point, a fingertip mask being defined by the area extending between the first finger joint and the fingertip point.