Latent Fingerprint Image Segmentation Using Fractal Dimension Features and Weighted Extreme Learning Machine Ensemble

Latent fingerprints are fingerprints unintentionally left at a crime scene. Due to the poor quality and often complex image background and overlapping patterns characteristic of latent fingerprint images, separating the fingerprint region-of-interest from complex image background and overlapping patterns is a very challenging problem. In this paper, we propose a latent fingerprint segmentation algorithm based on fractal dimension features and weighted extreme learning machine. We build feature vectors from the local fractal dimension features and use them as input to a weighted extreme learning machine ensemble classifier. The patches are classified into fingerprint and nonfingerprint classes. We evaluated the proposed segmentation algorithm by comparing the results with the published results from the state of the art latent fingerprint segmentation algorithms. The experimental results of our proposed approach show significant improvement in both the false detection rate (FDR) and overall segmentation accuracy compared to the existing approaches.