Latent fingerprints, are the oftentimes invisible patterns made by fingerprints that are usually left at crime investigations or on objects recovered from crime scenes, and forensically analyzed by latent fingerprint experts with the application of chemical or physical methods. Latent fingerprints recognition is very useful in law enforcement and forensics applications. However, automated matching of latent fingerprints with a gallery of live scan images is very challenging due to several compounding factors such as noisy background, poor ridge structure, and overlapping unstructured noise. In order to efficiently match latent fingerprints, an effective enhancement module is a necessity so that it can facilitate correct minutiae extraction. We have develop a research based project in which we implement Progressive Generative Adversarial Network a NVIDIA’s research for latent fingerprint enhancement algorithm to enhance the poor quality ridges and predict the ridge information. It helps the standard feature extraction and matching algorithms to boost latent fingerprints matching performance. The core advantage of progressive GAN over simple GAN’s is that we can create the images with high resolution as well.
SlimLoigx 2020. All Rights Reserved