20230075233. SYNTHETIC HUMAN FINGERPRINTS simplified abstract (THE REGENTS OF THE UNIVERSITY OF CALIFORNIA)

From WikiPatents
Jump to navigation Jump to search

SYNTHETIC HUMAN FINGERPRINTS

Organization Name

THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor(s)

Mohammad Sadegh Riazi of San Diego CA (US)

Seyed Mohammad Chavoshian of San Diego CA (US)

Farinaz Koushanfar of San Diego CA (US)

SYNTHETIC HUMAN FINGERPRINTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230075233 titled 'SYNTHETIC HUMAN FINGERPRINTS

Simplified Explanation

The patent application describes a system for generating synthetic human fingerprints using a combination of machine learning techniques. The system includes a processor and memory that stores instructions for performing various operations. These operations involve receiving real fingerprints from a database or sensor, training a generative adversarial network to learn the distribution of real fingerprints, and training a super-resolution engine to transform low-resolution synthetic fingerprints into high-resolution fingerprints. The system then provides the trained super-resolution engine with low-resolution synthetic fingerprints generated by the trained generative adversarial network, and outputs high-resolution synthetic fingerprints in response.

  • The system uses machine learning techniques to generate synthetic human fingerprints.
  • It trains a generative adversarial network to learn the distribution of real fingerprints.
  • It trains a super-resolution engine to transform low-resolution synthetic fingerprints into high-resolution fingerprints.
  • The system can generate high-resolution synthetic fingerprints based on low-resolution synthetic fingerprints provided by the generative adversarial network.

Potential Applications

  • Forensic investigations: Synthetic fingerprints can be used to test the accuracy and reliability of fingerprint recognition systems.
  • Biometric authentication: Synthetic fingerprints can be used to improve the performance and robustness of fingerprint recognition systems.
  • Research and development: Synthetic fingerprints can be used for research purposes, such as studying fingerprint patterns and their variations.

Problems Solved

  • Lack of sufficient real fingerprint data for training and testing fingerprint recognition systems.
  • Difficulty in generating high-resolution synthetic fingerprints that closely resemble real fingerprints.

Benefits

  • Provides a solution for generating synthetic fingerprints that can be used for various applications.
  • Enables the training and testing of fingerprint recognition systems using a large dataset of synthetic fingerprints.
  • Improves the quality and resolution of synthetic fingerprints, making them more realistic and useful for research and development purposes.


Original Abstract Submitted

in some embodiments, there is provided a system for generating synthetic human fingerprints. the system includes at least one processor and at least one memory storing instructions which when executed by the at least one processor causes operations, such as receiving, from a database and/or a sensor, at least one real fingerprint; training, based on the at least one real fingerprint, a generative adversarial network to learn a distribution of real fingerprints; training a super-resolution engine to learn to transform low resolution synthetic fingerprints to high-resolution fingerprints; providing to the trained super resolution engine at least one low resolution synthetic fingerprint that is generated as an output by the trained generative adversarial network; and in response to the providing, outputting, by trained super resolution engine, at least one high resolution synthetic fingerprint.

Retrieved from "http://wikipatents.org/index.php?title=20230075233._SYNTHETIC_HUMAN_FINGERPRINTS_simplified_abstract_(THE_REGENTS_OF_THE_UNIVERSITY_OF_CALIFORNIA)&oldid=20801"