Finger region localisation

Filtering the image using a simple mask will give a large response at the transition from background to finger. These large responses are located and used as detected finger edge. The function will return the location of these edges and will return a binary mask indicating the finger region.
Note that the implementation assumes that the upper edge is located in the top-half of the image and that the bottom edge is located in the lower-half of the image.

Literature:
- "Finger vein recognition using minutia-based alignment and local binary
pattern-based feature extraction" E.C. Lee, H.C. Lee and K.R. Park
International Journal of Imaging Systems and Technology
Volume 19, Issue 3, September 2009, Pages 175-178
doi: 10.1002/ima.20193

Comments:
Please leave a comment, if you like it, find a bug, or know (made) good improvements to the code.