Patch-based Segmentation of Latent Fingerprint Images Using Convolutional Neural Network

Abstract

Latent fingerprint segmentation involves marking out all the foreground regions accurately in a latent fingerprint image, but due to poor quality images and complex background, segmentation of latent fingerprint images is one of the most difficult tasks in automatic latent fingerprint recognition systems. In this article, we propose a patch-based technique for segmentation of latent fingerprint images, which uses Convolutional Neural Network (CNN) to classify patches. CNN has recently shown impressive performance in the field of pattern recognition, classification, and object detection, which inspired us to use CNN for this complex task. We trained the CNN model using SGD to classify image patches into fingerprint and non-fingerprint classes followed by proposed false patch removal technique, which uses “majority of neighbors” to remove the isolated and miss-classified patches. Finally, based on the final class of patches, an ROI is constructed to mark out the foreground from the background of latent fingerprint images. We tested our model on IIIT-D latent fingerprint database and the experimental results show improvements in the overall accuracy compared to existing methods.