Shape Features for Candidate Photo Selection in Sketch Recognition

Sketch recognition for forensic applications is a very challenging task and several solutions have been recently proposed. Considering that real mug shot databases can be very large, one important aspect to consider in this scenario is also the efficiency of the search procedure. This work proposes the use of shape features for a preliminary selection of the candidate photos to be successively analyzed by more complex state-of-the-art techniques. The proposed features can be computed and matched in a very short time, and at the same time they are able to significantly reduce the search space, thus allowing to speed up the recognition process.