Fingerprint Entropy and Identification Capacity Estimation Based on Pixel-level Generative Modelling
| Autor: | Soren Forchhammer, Martin Aastrup Olsen, Soren Sk. Christensen, Metodi P. Yankov, Mikkel Bille Stegmann |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer Networks and Communications
Computer science Feature extraction 0211 other engineering and technologies ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Biometric entropy 02 engineering and technology Fingerprint recognition Entropy estimation Entropy (classical thermodynamics) Entropy (information theory) Entropy (energy dispersal) Safety Risk Reliability and Quality Entropy (arrow of time) 021110 strategic defence & security studies Pixel Entropy (statistical thermodynamics) business.industry Pattern recognition Mutual information Biometric capacity Generative modelling Generative model Computer Science::Computer Vision and Pattern Recognition Affine transformation Artificial intelligence business Entropy (order and disorder) |
| Zdroj: | Yankov, M P, Olsen, M A, Stegmann, M B, Christensen, S S & Forchhammer, S 2020, ' Fingerprint Entropy and Identification Capacity Estimation Based on Pixel-level Generative Modelling ', IEEE Transactions on Information Forensics and Security, vol. 15, pp. 56-65 . https://doi.org/10.1109/TIFS.2019.2916406 |
| DOI: | 10.1109/TIFS.2019.2916406 |
| Popis: | A family of texture-based generative models for fingerprint images is proposed. The generative models are used to estimate upper bounds on the image entropy for systems with small sensor acquisition. The identification capacity of such systems is then estimated using the mutual information between different samples from the same finger. Similar to the generative model for entropy estimation, pixel-level model families are proposed for estimating the similarity between fingerprint images with a given global affine transformation. These models are used for mutual information estimation, and are also adopted to compensate for local deformations between samples. Finally, it is shown that sensor sizes as small as $52\times 52$ pixels are potentially sufficient to discriminate populations as large as the entire world population that ever lived, given that the complexity-unconstrained recognition algorithm is available which operates on the lowest possible pixel level. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|