Automatic Latent Fingerprint Segmentation
This work addresses the challenge of accurately segmenting latent fingerprints for forensic analysis, offering an incremental improvement over existing methods.
The paper tackles the problem of automatic latent fingerprint segmentation by introducing SegFinNet, a method that combines fully convolutional neural networks and detection-based approaches to process entire latent images, resulting in outperforming both human markup and state-of-the-art algorithms on three databases and boosting the hit rate of a fingerprint matcher.
We present a simple but effective method for automatic latent fingerprint segmentation, called SegFinNet. SegFinNet takes a latent image as an input and outputs a binary mask highlighting the friction ridge pattern. Our algorithm combines fully convolutional neural network and detection-based approaches to process the entire input latent image in one shot instead of using latent patches. Experimental results on three different latent databases (i.e. NIST SD27, WVU, and an operational forensic database) show that SegFinNet outperforms both human markup for latents and the state-of-the-art latent segmentation algorithms. We further show that this improved cropping boosts the hit rate of a latent fingerprint matcher.