Automatic Latent Fingerprint Segmentation
Autor: | Anil K. Jain, Dinh-Luan Nguyen, Kai Cao |
---|---|
Rok vydání: | 2018 |
Předmět: |
FOS: Computer and information sciences
021110 strategic defence & security studies Latent image Markup language Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL 0211 other engineering and technologies Process (computing) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Binary number Pattern recognition 02 engineering and technology Convolutional neural network ComputingMethodologies_PATTERNRECOGNITION 0202 electrical engineering electronic engineering information engineering Hit rate NIST 020201 artificial intelligence & image processing Segmentation Artificial intelligence business |
Zdroj: | BTAS |
DOI: | 10.48550/arxiv.1804.09650 |
Popis: | 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. Comment: Accepted (Oral) in BTAS 2018 |
Databáze: | OpenAIRE |
Externí odkaz: |