Latent Fingerprint Image Segmentation Using Deep Neural Network

Abstract

We present a deep artificial neural network (DANN) model that learns latent fingerprint image patches using a stack of restricted Boltzmann machines (RBMs), and uses it to perform segmentation of latent fingerprint images. Artificial neural networks (ANN) are biologically inspired architectures that produce hierarchies of maps through learned weights or filters. Latent fingerprints are fingerprint impressions unintentionally left on surfaces at a crime scene. To make identifications or exclusions of suspects, latent fingerprint examiners analyze and compare latent fingerprints to known fingerprints of individuals. 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 very challenging. Our proposed DANN model based on RBMs learns fingerprint image patches in two phases. The first phase (unsupervised pre-training) involves learning an identity mapping of the input image patches. In the second phase, fine-tuning and gradient updates are performed to minimize the cost function on the training dataset. The resulting trained model is used to classify the image patches into fingerprint and non-fingerprint classes. We use the fingerprint patches to reconstruct the latent fingerprint image and discard the non-fingerprint patches which contain the structured noise in the original latent fingerprint. The proposed model is evaluated by comparing the results from the state-of-the-art latent fingerprint segmentation models. The results of our evaluation show the superior performance of the proposed method.