Singular points are the regions where large changes of orientation happens and they are classified in core and delta. The singularities are very useful for fingerprint classification and for alignment purpose used during the matching (e.g., fingercode based matching). A simple way to compute the singularities is to use the Poincare method. For each point i,j of the orientation map are computed the Poincare index P(i,j) as the sum of the difference between the orientation of the point i,j and their neighbours.
Depending of the value of P(i,j) the point may be identified as core or delta. if P(i,j) is equal to 360 or 180 the point is core, but if the P(i,j) is equal to -180 then the point is a delta. In any other case the point is not singular.
The following figure shows an example of core and delta extraction.
 original image |
 core (red) and delta (green) detection |